A Project report on

“IDENTIFICATION OF FAKE PROFILES USING

ARTIFICIAL NEURAL NETWORKS”

Submitted in partial fulfillment of the requirement for the

award of the degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING

Submitted by
B.RAMANI(19X51A0507)

Under the Esteemed Guidance of

Mr. M. AMARESWARA KUMAR, M.Tech.

Assistant Professor, Department of CSE

SANTHIRAM ENGINEERING COLLEGE:: NANDYAL

Accredited by NAAC (Grade-A), An ISO 9001:2015 Certified Institution,
2(f) and 12(b) recognition by UGC Act, 1956
(Approved by AICTE, New Delhi: Permanently Affiliated to J.N.T. University, Anantapuramu, A.P.)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

YEAR: 2019-2023
 A Project report on

“IDENTIFICATION OF FAKE PROFILES USING

ARTIFICIAL NEURAL NETWORKS”

Submitted in partial fulfillment of the requirement for the

award of the degree of

BACHELOR OF TECHNOLOGY
IN
COMPUTER SCIENCE AND ENGINEERING

Submitted by
B.RAMANI(19X51A0507)

Under the Esteemed Guidance of

Mr. M. AMARESWARA KUMAR, M.Tech.

Assistant Professor, Department of CSE

SANTHIRAM ENGINEERING COLLEGE:: NANDYAL

Accredited by NAAC (Grade-A), An ISO 9001:2015 Certified Institution,
2(f) and 12(b) recognition by UGC Act, 1956
(Approved by AICTE, New Delhi: Permanently Affiliated to J.N.T. University, Anantapuramu, A.P.)

DEPARTMENT OF COMPUTER SCIENCE AND ENGINEERING

YEAR: 2019-2023
 SANTHIRAM ENGINEERING COLLEGE: NANDYAL
Accredited by NAAC (Grade-A), An ISO 9001:2015 Certified Institution,
2(f) and 12(b) recognition by UGC Act, 1956
(Approved by AICTE, New Delhi: Permanently Affiliated to J.N.T. University, Anantapuramu, A.P.)

CERTIFICATE

This is to certify that the dissertation entitle “IDENTIFICATION OF FAKE PROFILES

USING ARTIFICIAL NEURAL NETWORKS” that is being submitted by
B.RAMANI(19X51A0507) for partial fulfillment of the award of the Degree of Bachelor of
Technology in COMPUTER SCIENCE AND ENGINEERING the SANTHIRAM
ENGINEERING COLLEGE, Nandyal (Permanently Affiliated to J.N.T.U Anantapuramu) is a
record of bonafied work carried out by her under our guidance and supervision. The results
embodied in this project have not been submitted to any other university for the award of any
Degree.

Signature of the Head of the Department: Signature of the Project Guide:

Dr.S.MD.FAROOQ, Ph. D Mr. M. AMRESWARA KUMAR, M.Tech,
Professor & HOD Assistant Professor

Signature of the External Examiner:

Date of Examination:
 ACKNOWLEDGEMENT

This will certainly not be complete without acknowledgements paid to all these who
have helped me in doing my project work.

I manifest my heartier thankfulness pertaining to my contentment over

Mr.M.AMARESHWARA KUMAR garu, as projects guide with whose adroit
concomitance the excellence has been exemplified in bringing out this project work with
artistry.

It is a great pleasure to acknowledge my profound sense of gratitude to the Head of

Department Dr.S.MD.FAROOQ garu, coordinator of Mr.M. AMARESWARA KUMAR
garu, for his valuable inspiring guidance, comments and suggestions and encouragement
towards the course of this project.

Involuntarily, I am precious to divulge my sincere gratefulness to the principal, Dr.M.V.

SUBRAMANYAM garu, who has been observed posing valance in abundance forwards our
individuality to acknowledge my project work tendentiously.

At the outset we thank Honorable chairman Dr.M. SANTHIRAMUDU garu,

correspondent, Santhiram Engineering College for providing me with good facilities and his
moral support throughout the course.

I also express the overall exhilaration and gratitude to all the Teaching and Non- Teaching
staff of CSE Dept., who admitted my project work and accentuated my attitude.

I also extend my heartfelt and sincere gratitude to my beloved parents for their
tremendous motivation and moral support.

B. RAMANI(19x51A0507)
 TABLE OF CONTENTS

S.NO DESCRIPTION PAGE NO

1. INTRODUCTION 1-2
1.1 Introduction to the Social Media Platforms 1
1.2 Objective of the Project 2
2. LITERATURE SURVEY 3-6
2.1 Detection of Fake Accounts 3
2.2 Audit and Analysis of Impostors 3
2.3 A Comprehensive Review 4
2.4 Online Social Networks Threats and Solution 4
2.5 Advanced Social Engineering Attacks 5
2.6 Analysis of Social Network Sybil Defenses 5
2.7 Anomalous Behaviour in Temporal Networks 6
2.8 Scalable Community Detection Using 6
MapReduce
3. SYSTEM ANALYSIS 7-19
3.1 Existing System 7
3.1.1 Disadvantages of Existing System 7

3.2 Proposed System 8

3.2.1 Advantages of Proposed System 8

3.3 Process Model Used with Justification 9-16

3.3.1 Requirements Gathering Stage 10
3.3.2 Analysis Stage 11
3.3.3 Designing Stage 12
3.3.4 Development (Coding) Stage 13
3.3.5 Integration & Test Stage 14
3.3.6 Installation & Acceptance test 15
3.3.7 Maintenance 16

3.4 Software Requirement Specification 16-19

3.4.1 Overall Description 16
3.4.2 External Interface Requirements 17
 3.4.3 Non -Functional Requirements 18
3.4.4 Hardware Requirements 19
3.4.5 Software Requirements 19
4. SYSTEM DESIGN 20-33
4.1 Modules 14
4.1.1 User Interface design 20
4.1.2 Login Module 20
4.1.3 Train the Data using ANN 20
4.1.4 View the Trained Data 20
4.1.5 Prediction of Fake Profiles 20
4.2 Introduction to UML 20
4.3 Class Diagram 21
4.4 Use case Diagram 22
4.5 Sequence Diagram 24
4.6 Collaboration Diagram 25
4.7 Component Diagram 26
4.8 Deployment Diagram 27
4.9 Activity Diagram 28
4.10 Dataflow Diagram 29
5. IMPLEMENTATION 34-46
5.1 Python 34
5.2 Introduction to Machine Learning 36
5.3 Approaches 37
5.4 Use of ANN Algorithm 37
5.5 Sample Code 41

6. IMPLEMENTATION & TESTING 47-49

6.1 Implementation 47
6.2 Testing 47
6.3 System Testing 47
6.4 Module Testing 48
6.5 Integration Testing 48
6.6 Acceptance Testing 48

7. SCREENSHOTS 50-60
7.1 Home Page 50
7.2 Admin Page 51
7.3 Generate ANN Model 52
7.4 View ANN Train Model 53
7.5 ANN Accuracy 54
7.6 User Page 56
7.7 Text Data Attribute Values 57
8. CONCLUSION 61
9. REFERENCES 62
10. ANNEXURE
 LIST OF FIGURES

FIG. No. NAME OF THE FIGURES PAGE NO

3.3 Umbrella Model 9

3.3.1 Requirements Gathering Stage 10
3.3.2 Analysis Stage 11
3.3.3 Designing Stage 12
3.3.4 Development (Coding) Stage 13
3.3.5 Integration and Test Stage 14
3.3.6 Installation and Acceptance Test 15
4.3 Class Diagram 21
4.4 Use case Diagram for Admin 22
4.4.1 Use case Diagram for User 23
4.5 Sequence Diagram 24
4.6 Collaboration Diagram 25
4.7 Component Diagram for Admin 26
4.7.1 Component Diagram for User 27
4.8 Deployment Diagram 28
4.9 Activity Diagram for Admin 28
4.9.1 Activity Diagram for User 29
4.10 Data Flow Diagram 30
5.2 Machine Learning process 36
5.4 Process of ANN Algorithm 38
7.1 Home Page 50
7.2 Admin Page 51
7.3 Generate ANN Model 52
7.4 View ANN Train Model 53
7.5 ANN Accuracy Train Page 54
7.5.1 All Train Data and Records 55
7.6 User Account Check 56
7.7 User Account to Text the Data 57
Value Attributes
7.7.1 Account Details Predicted as 58
Fake or Genuine
7.7.2 Sample 1 Data to Test Genuine 59
or Fake
7.7.3 Sample 2 Data to Test Genuine 60
or Fake
 LIST OF TABLES

T.NO NAME OF THE TABLE PAGE NO

4.11 UML Notations 33

6.2 Test Cases 49

 ABSTRACT
These days, there is a noticeable increase in applied sciences. Mobile phones are
becoming smarter. Technology is associated with online social networks, which have emerged
as a part of everyone's life in terms of making new friends and retaining friends, as well as
making their hobbies easier. However, the increase in online networking causes various
problems, such as fabricating their profile. In this project, we employ computing device
learning, specifically a synthetic neural community, to identify whether a Facebook buddy
request is legitimate. We also outline the training and libraries that will be used. We also
discuss the sigmoid feature and how weights are determined and used Finally, we reflect on
consideration on the parameters of the social community web page which are utmost
necessary in the furnished solution. The use of social media and other online platforms has
grown rapidly in recent years, leading to an increase in the number of fake profiles being
created. Fake profiles can be used for a variety of purposes, such as spreading misinformation,
manipulating public opinion, or committing fraud. As such, it is important to develop methods
for identifying and removing these profiles. The data that their users submit is the source of
income for social media platforms. The typical social media user is unaware that they are
waiving certain legal protections by using the site. To the detriment of its users, social media
platforms stand to gain a great deal. Facebook generates income from adverts and user data
every time a user posts material to the platform, such as a new location, new images, likes,
dislikes, and tags other people in the content. It is via user data that social media platforms
generate income. Normal users have no idea that they are giving up rights by using a social
networking site. The purpose of this project is to utilize machine learning, specifically an
artificial neural network, to predict whether the friend request is genuine or not in social
media platforms.
 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER – 1
INTRODUCTION
1.1 INTRODUCTION TO THE SOCIAL MEDIA PLATFORM

In 2017 Facebook reached a total population of 2.46 billion users making it the most popular choice of
socialmedia. Social media networks make revenues from the data provided by users. The average user does
not know that their rights are given up the moment they use the social media network's service. Social media
companies have a lot to gain at the expense of the user. Every time a user shares a new location, new photos,
likes, dislikes, and tag other users in content posted, Facebook makes revenue via advertisements and data.
More specifically, the average American user generates about $26.76 per quarter. That number adds up
quickly when millions of users are involved. In today's digital age, the ever-increasing dependency on
computer technology has left the average citizen vulnerable to crimes such as data breaches and possible
identity theft. These attacks can occur without notice and often without notification to the victims of a data
breach. At this time, there is little incentive for social networks to improve their data security. These
breaches often target social media networks such as Facebook and Twitter. They can also target banks and
other financial institutions. There seems to be a newsworthy issue involving social media networks getting
hacked every day. Recently, Facebook had a data breach which affected about 50 million users. Facebook
provides a set of clearly defined provisions that explain what they do with the user's data. The policy does
very little to prevent the constant exploitation of security and privacy. Fake profiles seem to slip through
Facebook's built-in security features.

The other dangers of personal data being obtained for fraudulent purposes is the presence of bots and
fake profiles. Bots are programs that can gather information about the user without the user even knowing.
This process is known as web scraping. What is worse, is that this action is legal. Bots can be hidden or
come in the form of a fake friend request on a social network site to gain access to private information. The
solution presented in this paper intends to focus on the dangers of a bot in the form of a fake profile on your
social media. This solution would come in the form of an algorithm. The language that we chose to use is
Python. The algorithm would be able to determine if a current friend request that a user gets online is an
actual person or if it is a bot or it is a fake friend request fishing for information. Our algorithm would work
with the help of the social media companies, as we would need a training dataset from them to train our
model and later verify if the profiles are fake or not. The algorithm could even workas a traditional layer on
the user's web browser as a browser plug-in.

Dept of CSE SREC Page 1

 Identification Of Fake Profiles Using Artificial Neural Networks

1.2 OBJECTIVE OF THE PROJECT:

Social media networks make revenues from the data provided by users. The average user does not know
that their rights are given up the moment they use the social media network's service. Technology is
associated with online social networks, which have emerged as a part of everyone's life in terms of making
new friends and retaining friends, as well as making their hobbies easier. However, the increase in online
networking causes various problems, such as fabricating their profile. Social media companies have a lot to
gain at the expense of the user. Every time a user shares a new location, new photos, likes, dislikes, and tag
other users in content posted, Facebook makes revenue via advertisements and data. Social media networks
make revenues from the data provided by users. The average user does not know that their rights are given
up the moment they use the social media network's service. Social media companies have a lot to gain at the
expense of the user. Every time a user shares a new location, new photos, likes, dislikes, and tag other users
in content posted, Facebook makes revenue via advertisements and data. In this paper, we use machine
learning, namely an artificial neural network to determine what the chances that Facebook friend
request is authentic or not. The typical social media user is unaware that they are waiving certain legal
protections by using the site. To the detriment of its users, social media platforms stand to gain a great deal.
The purpose of this project is to utilize machine learning, specifically an artificial neural network, to predict
whether the friend request is genuine or not in social media platforms.

Dept of CSE SREC Page 2

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER - 2
LITERATURE SURVEY

2.1 DETECTION OF FAKE ACCOUNTS

Users increasingly rely on the trustworthiness of the information exposed on Online Social Networks
(OSNs). In addition, OSN providers base their business models on the marketability of this information.
However, OSNs suffer from abuse in the form of the creation of fake accounts, which do not correspond to
real humans. Fakes can introduce spam, manipulate online rating, or exploit knowledge extracted from the
network. OSN operators currently expend significant resources to detect, manually verify, and shut down fake
accounts. Tuenti, the largest OSN in Spain, dedicates 14 full-time employees in that task alone, incurring a
significant monetary cost. Such a task has yet to be successfully automated because of the difficulty in reliably
capturing the diverse behaviour of fake and real OSN profiles. We introduce a new tool in the hands of OSN
operators, which we call SybilRank. It relies on social graph properties to rank users according to their
perceived likelihood of being fake (Sybils). SybilRank is computationally efficient and can scale to graphs
with hundreds of millions of nodes, as demonstrated by our Hadoop prototype. We deployed SybilRank in
Tuenti's operation center. We found that ∼90% of the 200K accounts that SybilRank designated as most likely
to be fake, actually warranted suspension. On the other hand, with Tuenti's current user-report-based approach
only ∼5% of the inspected accounts are indeed fake.

2.2 AUDIT AND ANALYSIS OF IMPOSTORS:

In the present generation, the social life of every person has become associated with online social
networks (OSN). These sites have made drastic changes in the way we socialize. Making friends and keeping
in contact with them as well as being updated of their activities, has become easier. But with their rapid
growth, problems like fake profiles, online impersonation have also increased. The risk lies in the fact that
anybody can create a profileto impersonate a real person on the OSN. The fake profile could be exploited to
build online relationship with a targeted person purely through online interactions with the friends of victim.
In present work, we have proposed experimental framework with which detection of fake profile is feasible
within the friend list, however this framework is restricted to a specific online social networking site namely
Facebook. This framework extracts data from the friend list and uses it to classify them as real or fake by
using unsupervised and supervised machine learning.

Dept of CSE SREC Page 3

 Identification Of Fake Profiles Using Artificial Neural Networks

2.3 A COMPREHENSIVE REVIEW:

Fake profile detection techniques in large-scale online social networks: In the present era, online social
networks are the most popular and rapid information propagation applications on the Internet. People of all
ages spend most of their time on social networking sites. Huge volumes of data are being created and shared
through social networks around the world. These interests have given rise to illegitimate users who engage in
fraudulent activities against social network users. On social networks, fake profile creation is considered to
cause more harm than any other form of cyber-crime. This crime has to be detected even before the user is
notified about the fake profile creation. Many algorithms and methods, most of which use the huge volume of
unstructured data generated from social networks, have been proposed for the detection of fake profiles. This
study presents a survey of the existing and latest technical work on fake profile detection.
2.4 ONLINE SOCIAL NETWORKS THREATS AND SOLUTIONS:

Many online social network (OSN) users are unaware of the numerous security risks that exist in these
networks, including privacy violations, identity theft, and sexual harassment, just to name a few. According to
recent studies, OSN users readily expose personal and private details about themselves, such as relationship
status, date of birth, school name, email address, phone number, and even home address. This information,
if put into the wronghands, can be used to harm users both in the virtual world and in the real world. These
risks become even more severe when the users are children. In this paper, we present a thorough review of the
different security and privacy risks on social networks, fake profile creation is considered to cause more harm
than any other form of cyber-crime. This crime has to be detected even before the user is notified about the
fake profile creation. Many algorithms and methods, which threaten the well-being of OSN usersin general,
and children in particular. In addition, we present an overview of existing solutions that can provide better
protection, security, and privacy for OSN users. We also offer simple-to-implement recommendations for
OSN users, which can improve their security and privacy when using these platforms. Furthermore, it has
some information, if put into the wrong hands, can be used to harm users both in the Virtualworld. As the use
of OSNs becomes progressively more embedded in users' daily lives, personal information becomes easily
exposed and abused. Information harvesting, by both the OSN operator itself and by third-party commercial
companies, has recently been identified as a significant security concern for OSN users. Companies can
exploit the harvested personal information for a variety of purposes, all of which can jeopardize a user's
privacy. The fake profile could be exploited to build online relationship with a targeted person purely through
online interactions with the friends of victim and we need to analyze the friend request is genuine or fake.

Dept of CSE SREC Page 4

 Identification Of Fake Profiles Using Artificial Neural Networks

2.5 ADVANCED SOCIAL ENGINEERING ATTACKS:

Social engineering has emerged as a serious threat in virtual communities and is an effective means to
attack information system. The services used by today's knowledge workers prepare the ground for
sophisticated social engineering attacks. The growing trend towards BYOD (bring your own device) policies
and the use of online communication and collaboration toolsin private and business environments aggravate
the problem. In globally acting companies, teams are no longer geographically co-located, but staffed just-in-
time. The decrease inpersonal interaction combined with a plethora of tools used for communication (e-mail,
IM, Skype, Dropbox, LinkedIn, Lync, etc.) create new attack vectors for social engineering attacks. Recent
attacks on companies such as the New York Times and RSA have shown that targeted spear-phishing attacks
are an effective, evolutionary step of social engineering attacks. Combined with zero-day-exploits, they
become a dangerous weapon that is often used by advanced persistent threats. This paper provides a
taxonomy of well-known social engineering attacks as well as a comprehensive overview of advanced social
engineering attacks on the knowledge worker.
2.6 ANALYSIS OF SOCIAL NETWORK-BASED SYBIL DEFENCES:
Recently, there has been much excitement in the research community over using social networks to
mitigate multiple identity, or Sybil, attacks. A number of schemes have been proposed, but they differ greatly
in the algorithms they use and in the networks upon which they are evaluated. As a result, the research
community lacks a clear understanding of how these schemes compare against each other, how well they
would work on real-world social networks with different structural properties, or whether there exist other
(potentially better) ways of Sybil defense. In this paper, we show that, despite their considerable differences,
existing Sybil defense schemes work by detecting local communities (i.e., clusters of nodes more tightly knit
than the rest of the graph) around a trusted node. Our finding has important implications for both existing and
future designs of Sybil defense schemes. First, we show that there is an opportunity to leverage the
substantial amount of prior work on general community detection algorithms in order to defend against Sybils.
Second, our analysis reveals the fundamental limits of current social network-based Sybil defences. We
demonstrate that networks with well-defined community structure are inherently more vulnerable to Sybil
attacks, and that, in such networks, Sybils can carefully target their links in order make their attacks more
effective. Our analysis reveals the fundamental limits of current social network-based Sybil defenses: We
demonstrate that networks with well-defined community structure are inherently more vulnerable to Sybil
attacks, and that, in such networks, Sybils can carefully target their links in order make their attacks more
effective.

Dept of CSE SREC Page 5

 Identification Of Fake Profiles Using Artificial Neural Networks

2.7 ANOMALOUS BEHAVIOUR IN TEMPORAL NETWORKS:

In this work we consider the problem of detecting anomalous behaviour and present a novel approach
that allows ‘behaviour’ to be classified as either to be normal or abnormal by checking the p-value associated
with the occurrence of the behaviour which is modelled following a binomial distribution within a discrete
time model. We investigate the problem of detecting anomalous behaviour by looking at how communication
evolves over time in a social network graph. Under the assumption that some nodes of the network could be
labelled qualitatively, we present a novel approach that allows us to infer a subset of nodes of the social
network which might share the same qualitative connotation. In other words, assuming one or more members
belong to some criminal organization, we wish to investigate how many other persons belong to the same
organization.We have tested our method in two datasets, VAST2008 and a Twitter Dataset (data collected in
2012), with encouraging results.
2.8 SCALABLE COMMUNITY DETECTION USING MAPREDUCE:
In this project, we present a community-detection solution for massive-scale social networks using
MapReduce, a parallel programming framework. We use a similarity metric to model the community
probability, and the model is designed to be parallelizable and scalable in the MapReduce framework. More
importantly, we propose a set of degree-based pre-processing and postprocessing techniques named DEPOLD
(Delayed Processing of Large Degree nodes) that significantly improve both the community-detection
accuracy and performance. We investigate the problem of detecting anomalous behaviour by looking at how
communication evolves over time in a social network graph. Under the assumption that some nodes of the
network could be labelled qualitatively, we present a novel approach that allows us to infer a subset of nodes
of the social network which might share the same qualitative connotation. With DEPOLD, delaying analysis
of 1% of high-degree nodes to the postprocessing stage reduces both processing time and storage space by
one order of magnitude. DEPOLD can be appliedto other graph-clustering problems. Furthermore, we design
and implement two similarity calculation algorithms using MapReduce with different computation and
communication characteristics in order to adapt to various system configurations. Finally, we conduct
experiments with publicly available datasets. Our evaluation demonstrates the effectiveness, efficiency, and
scalability of the proposed solution. Then we adopt an iterative expansion approach to find all the
communities in the graph. Empirical results show that for large networks in the order of millions of nodes, the
parallel version of the algorithm outperforms the traditional sequential approach to detect communities using
the M-measure. The result shows that for local community detection, when the data is too big for the original
M metric-based sequential iterative expansion approach to handle, our MapReduce version 3MA can finish.

Dept of CSE SREC Page 6

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER – 3
SYSTEM ANALYSIS
3.1 EXISTING SYSTEM:

In today's digital age, the ever-increasing dependency on computer technology has left the average
citizen vulnerable to crimes such as data breaches and possible identity theft. These attacks can occur
without noticeand often without notification to the victims of a data breach. Most fake profile detection is
done manually, either by platform administrators or by volunteer organizations. However, this is a slow and
labor-intensive process, and it is difficult to keep up with the sheer volume of profiles being created.
Additionally, manual review is subject to human error, and fake profiles can often be designed to be very
convincing.

3.1.1 Disadvantages of Existing System:

1. Slow and Labor-Intensive

Manual review is a slow and labor-intensive process, and it can be difficult to keep up with the
sheer volume of profiles being created.

2. Susceptible to Human Error

Human review is subject to human error, and fake profiles can often be designed to be very
convincing.

3. Limited Scale

Existing systems are limited in terms of the number of profiles that can be reviewed in a given
time period, making it difficult to keep up with the volume of new profiles being created.

4. Less Accuracy

It gets a less accuracy in the existing system because it is a human error and slow labor-intensive

Dept of CSE SREC Page 7

 Identification Of Fake Profiles Using Artificial Neural Networks

3.2 PROPOSED SYSTEM:

In this project, we use machine learning, namely an artificial neural network to determine what are the
chances that a friend request is authentic are or not. Each equation at each neuron (node) is put through a
sigmoid function. We use a training data set by Facebook or other social networks. To address these
challenges, the use of Artificial Neural Networks (ANNs) to identify fake profiles. ANNs are machine
learning models that can be trained to recognize patterns and features in data. By training an ANN on a
dataset of real and fake profiles, it can be used to identify fake profiles in real-time. The proposed system
would have several benefits over existing methods. It would be much faster and more efficient than manual
review, and it would be less susceptible to human error. Additionally, ANNs can be trained to recognize new
types of fake profiles as they emerge, making the system more flexible and adaptable over time.

3.2.1 Advantages of proposed system:

1. Speed and Efficiency

The proposed system would be much faster and more efficient than manual review, allowing
for the rapid identification of fake profiles.

2. Reduced Human Error

The proposed system would be less susceptible to human error, as it would rely on machine
learning models that have been trained on a large dataset of real and fake profiles.

3. Adaptability

The proposed system would be flexible and adaptable over time, as it could be updated to
recognize new types of fake profiles as they emerge.

4. Accuracy is High

In the proposed System the Accuracy is high compare to the Existing System

Dept of CSE SREC Page 8

 Identification Of Fake Profiles Using Artificial Neural Networks

3.3 PROCESS MODEL USED WITH JUSTIFICATION:

FIG 3.3: SDLC (UMBRELLA MODEL)

SDLC is stands for Software Development Life Cycle. It is a standard which is used by software industry to
develop good software.

Stages in SDLC:

 Requirement Gathering
 Analysis
 Designing
 Coding
 Testing
 Deployment
 Maintenance

Dept of CSE SREC Page 9

 Identification Of Fake Profiles Using Artificial Neural Networks

3.3.1 Requirements Gathering stage:

The requirements gathering process takes as its input the goals identified in the high-level requirements
section of the project plan. Each goal will be refined into a set of one or more requirements. These
requirements define the major functions of the intended application, define operational data areas and
reference data areas, and define the initial data entities. Major functions include critical processes to be
managed, as well as mission critical inputs, outputs and reports. A user class hierarchy is developed and
associated with these major functions, data areas, and data entities. Each of these definitions is termed a
Requirement. Requirements are identified by unique requirement identifiers and, at minimum, contain a
requirement title and textual description.

FIG 3.3.1: Requirements Gathering stage

These requirements are fully described in the primary deliverables for this stage: the Requirements
Document and the Requirements Traceability Matrix (RTM). The requirements document contains complete
descriptions of each requirement, including diagrams and references to external documents as necessary.
Note that detailed listings of database tables and fields are not included in the requirements document. The
title of each requirement is also placed into the first version of the RTM, along with the title of eachgoal
from the project plan. The purpose of the RTM is to show that the product components developed
during each stage of the software development lifecycle are formally connected to the components
developed in prior stages.

Dept of CSE SREC Page 10

 Identification Of Fake Profiles Using Artificial Neural Networks

In the requirements stage, the RTM consists of a list of high-level requirements, or goals, by title,
with a listing of associated requirements for each goal, listed by requirement title. In this hierarchical
listing, the RTM shows that each requirement developed during this stage is formally linked to a
specific product goal. In this format, each requirement can be traced to a specific product goal, hence
the term requirements traceability.

The outputs of the requirements definition stage include the requirements document, the RTM, and an
updated project plan.

 Feasibility study is all about identification of problems in a project.

 No. of staff required to handle a project is represented as Team Formation, in this case only modules
are individual tasks will be assigned to employees who are working for that project.

 Project Specifications are all about representing of various possible inputs submitting to the server
and corresponding outputs along with reports maintained by administrator.

3.3.2 Analysis Stage:

The planning stage establishes a bird's eye view of the intended software product, and uses this to
establish the basic project structure, evaluate feasibility and risks associated with the project, and describe
appropriate management and technical approaches.

FIG 3.3.2: Analysis Stage

Dept of CSE SREC Page 11

 Identification Of Fake Profiles Using Artificial Neural Networks

The most critical section of the project plan is a listing of high-level product requirements, also
referred to as goals. All of the software product requirements to be developed during the requirements
definition stage flow from one or more of these goals. The minimum information for each goal consists of a
title and textual description, although additional information and references to external documents may be
included. The outputs of the project planning stage are the configuration management plan, the quality
assurance plan, and the project plan and schedule, with a detailed listing of scheduled activities for the
upcoming Requirements stage, and high-level estimates of effort for the out stages.

3.3.3 Designing Stage:

The design stage takes as its initial input the requirements identified in the approved requirements
document. For each requirement, a set of one or more design elements will be produced as a result of
interviews, workshops, and/or prototype efforts. Design elements describe the desired software features in
detail, and generally include functional hierarchy diagrams, screen layout diagrams, tables of business rules,
business process diagrams, pseudo code, and a complete entity-relationship diagram with a full data
dictionary. These design elements are intended to describe the software in sufficient detail that skilled
programmers may develop the software with minimal additional input.

FIG 3.3.3: Designing Stage

Dept of CSE SREC Page 12

 Identification Of Fake Profiles Using Artificial Neural Networks

When the design document is finalized and accepted, the RTM is updated to show that each design
element is formally associated with a specific requirement. The outputs of the design stage are the design
document, an updated RTM, and an updated project plan.

3.3.4 Development (Coding) Stage:

The development stage takes as its primary input the design elements described in the approved design
document. For each design element, a set of one or more software artifacts will be produced. Software
artifacts include but are not limited to menus, dialogs, and data management forms, data reporting formats,
and specialized procedures and functions. Appropriate test cases will be developed for each set of
functionally related software artifacts, and an online help system will be developed to guide users in their
interactions with the software.

FIG 3.3.4: Development (Coding) Stage

The RTM will be updated to show that each developed artifact is linked to a specific design element,
and that each developed artifact has one or more corresponding test case items. At this point, the RTM is in
its final configuration. The outputs of the development stage include a fully functional set of software that
satisfies the requirements and design elements previously documented, an online help system that describes
a software.

Dept of CSE SREC Page 13

 Identification Of Fake Profiles Using Artificial Neural Networks

The operation of the software, an implementation map that identifies the primary code entry points for
all major system functions, a test plan that describes the test cases to be used to validate the correctness and
completeness of the software, an updated RTM, and an updated project plan.

3.3.5 Integration & Test Stage:

During the integration and test stage, the software artifacts, online help, and test data are migrated from
the development environment to a separate test environment. At this point, all test cases are run to verify the
correctness and completeness of the software. Successful execution of the test suite confirms a robust and
complete migration capability. During this stage, reference data is finalized for production use and
production users are identified and linked to their appropriate roles. The final reference data (or links to
reference data source files) and production user list are compiled into the Production Initiation Plan.

FIG 3.3.5: Integration & Test Stage

The outputs of the integration and test stage include an integrated set of software, an online help
system, an implementation map, a production initiation plan that describes reference data and production
users, an acceptance plan which contains the final suite of test cases, and an updated project plan.

Dept of CSE SREC Page 14

 Identification Of Fake Profiles Using Artificial Neural Networks

3.3.6 Installation & Acceptance Test:

During the installation and acceptance stage, the software artifacts, online help, and initial production
data are loaded onto the production server. At this point, all test cases are run to verify the correctness and
completeness of the software. Successful execution of the test suite is a prerequisite to acceptance of the
software by the customer.

After customer personnel have verified that the initial production data load is correct and the test suite has
been executed with satisfactory results, the customer formally accepts the delivery of the software.

FIG 3.3.6: Installation & Acceptance Test

The primary outputs of the installation and acceptance stage include a production application, a
completed acceptance test suite, and a memorandum of customer acceptance of the software. Finally, the
PDR entersthe last of the actual labor data into the project schedule and locks the project as a permanent
project record. At this point the PDR "locks" the project by archiving all software items, the implementation
map, the source code, and the documentation for future reference.

Dept of CSE SREC Page 15

 Identification Of Fake Profiles Using Artificial Neural Networks

3.3.7 Maintenance:

Outer rectangle represents maintenance of a project, Maintenance team will start with requirement
study, understanding of documentation later employees will be assigned work and they will undergo
training on that particular assigned category. For this life cycle there is no end, it will be continued so on like
an umbrella (no ending point to umbrella sticks).

3.4. SOFTWARE REQUIREMENT SPECIFICATION:

3.4.1 Overall Description:

A Software Requirements Specification (SRS) – a requirements specification for a software system is a

complete description of the behaviour of a system to be developed. It includes a set of use cases that describe
all the interactions the users will have with the software. In addition to use cases, the SRS also contains non-
functional requirements. Non-functional requirements are requirements which impose constraints on the
design or implementation (such as performance engineering requirements, quality standards, or design
constraints).

System requirements specification: A structured collection of information that embodies the requirements
of a system. A business analyst, sometimes titled system analyst, is responsible for analysing the business needs
of their clients and stakeholders to help identify business problems and propose solutions. Within the systems
development lifecycle domain, the BA typically performs a liaison function between the business side of an
enterprise and the information technology department or external service providers. Projects are subject to three
sorts of requirements:

• Business requirements describe in business terms what must be delivered or accomplished to provide
value.

• Product requirements describe properties of a system or product (which could be one of several ways
to accomplish a set of business requirements.)

• Process requirements describe activities performed by the developing organization. For instance,
process requirements could specify. Preliminary investigation examines project feasibility, the likelihood the
system will be useful to the organization. The main objective of the feasibility study is to test the Technical,
Operational and Economical feasibility for adding new modules and debugging old running system. All
system is feasible if they are unlimited resources and infinite time. There are aspects in the feasibility study
portion of the preliminary investigation:

Dept of CSE SREC Page 16

 Identification Of Fake Profiles Using Artificial Neural Networks

3.4.1.1 Economic Feasibility

A system can be developed technically and that will be used if installed must still be a good
investment for the organization. In the economic feasibility, the development cost in creating the system is
evaluated against the ultimate benefit derived from the new systems. Financial benefits must equal or
exceed the costs. The system is economically feasible. It does not require any addition hardware or
software. Since the interface for this system is developed using the existing resources and technologies
available at NIC, there is nominalexpenditure and economic feasibility for certain.

3.4.1.2 Operational Feasibility

Proposed projects are beneficial only if they can be turned out into information system. That will
meet the organization’s operating requirements. Operational feasibility aspects of the project are to be
taken as an important part of the project implementation. This system is targeted to be in accordance with
the above- mentioned issues. Beforehand, the management issues and user requirements have been taken
into consideration. So, there is no question of resistance from the users that can undermine the possible
application benefits. The well-planned design would ensure the optimal utilization of the computer
resourcesand would help in the improvement of performance status.

3.4.1.3 Technical Feasibility

Earlier no system existed to cater to the needs of ‘Secure Infrastructure Implementation System’.
The currentsystem developed is technically feasible. It is a web-based user interface for audit workflow at
NIC-CSD. Thus, it provides an easy access to. the users. The database’s purpose is to create, establish and
maintain a workflow among various entities in order to facilitate all concerned users in their various
capacities or roles. Permission to the users would be granted based on the roles specified. Therefore, it
provides the technical guarantee of accuracy, reliability and security.

3.4.2 External Interface Requirements:

3.4.2.1 User Interface

The user interface of this system is a user-friendly python Graphical User Interface. The
application is provided with keyboard shortcuts with a facility to use most to trigger the required
actions.

Dept of CSE SREC Page 17

 Identification Of Fake Profiles Using Artificial Neural Networks

They act as shortcuts and provide an easy navigation with in their software. Appropriate error
handling isdone using exceptions in order to isolate abnormal results or conditions.

These messages are popped up to the user in the form of dynamic html or alert.

3.4.2.2 Hardware Interfaces

The interaction between the user and the console is achieved through python capabilities.

3.4.2.3 Software Interfaces

The required software is python.

3.4.2.4 Operating Environment

Windows XP.

3.4.3 Non-Functional Requirements:

Performance requirements:

Good bandwidth, less congestion on the network. Identifying the shortest root to reach the
destination toenhance the performance.

Safety requirements:

No harm is expected from the use of the application either to the OS or any data that resides on
the clientsystem.

Application security requirements:

The product is protected from unauthorized users from using it the system allows only
authenticated users towork on the application. The users of the system are students.

Dept of CSE SREC Page 18

 Identification Of Fake Profiles Using Artificial Neural Networks

3.4.4 Hardware Requirements:

 Speed - 1.1 Ghz

 Processor - intel i3 or above
 RAM - 256 GB
 Hard Disk - 20 GB
 Key Board - Standard Windows Keyboard

3.4.5 Software Requirements:

 Operating System - Windows10

 Programming Language - Python
 Scripting Language - Html, CSS, JavaScript

Dept of CSE SREC Page 19

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER – 4
SYSTEM DESIGN
4.1 MODULES
4.1.1 User Interface Design

Here User Module means an employee. When the User opens the website, he/she able to see the digital
dairysystem with visible of categories, companies and products. User Can see that company products and
choose what he/she want they will be buying the product.

4.1.2 Login Module:

A login page is an entry page to a website that requires user identification and authentication. Admin
can login by entering username and password combination. Authorized admin only can access the website.
Oncelogin is successful website can be accessed.

4.1.3 Train the Data Using ANN:

Once the model is built, we need to train it using a training dataset. During training, the weights and
biasesof the neurons are adjusted based on the error between the predicted output and the actual output. This
is done using an optimization algorithm such as gradient descent.

4.1.4 View the Trained Data:

After the train data we can view the data by generating the ANN algorithm by using some attribute values.

4.1.5 Prediction of Fake Profiles:

In this case you can see the trained data to easily classify the user profiles or friend request is
genuine or fake.

4.2 INTRODUCTION TO UML:

UML stands for Unified Modelling Language which is used in object-oriented software engineering.
Although typically used in software engineering it is a rich language that can be used to model an
application structure, behaviour and even business processes. which is designed to provide a standard way to
visualize the design of a system.

Dept of CSE SREC Page 20

 Identification Of Fake Profiles Using Artificial Neural Networks

It was created and developed by Grady Booch, Ivar Jacobson and James Rumbaugh at Rational
Software during 1994–95 with further development led by them through 1996. In 1997 it was adopted as a
standard bythe Object Management Group (OMG), and has been managed by this organization ever since. In
2000 the Unified Modelling Language was also accepted by the International Organization for
Standardization (ISO) as an approved ISO standard.

The System Design is done using UML DIAGRAMS. The following are the UML diagrams used:

4.3 CLASS DIAGRAM:

The class diagram is the main building block of object-oriented modeling. It is used both for general
conceptual modeling of the systematic of the application, and for detailed modeling translating the models
into programming code. Class diagrams can also be used for data modeling.

The classes in a class diagram represent both the main objects, interactions in the application and the
classes to be programmed. In the diagram, classes are represented with boxes which contain three parts:

 The upper part holds the name of the class

 The middle part contains the attributes of the class
 The bottom part gives the methods or operations the class can take or undertake

FIG 4.3: CLASS DIAGRAM

Dept of CSE SREC Page 21

 Identification Of Fake Profiles Using Artificial Neural Networks

4.4 USECASE DIAGRAM:

A use case diagram at its simplest is a representation of a user's interaction with the system and
depicting the specifications of a use case. A use case diagram can portray the different types of users of a
system and the various ways that they interact with the system. This type of diagram is typically used in
conjunction with the textual use case and will often be accompanied by other types of diagrams as well.

FIG 4.4: USECASE DIAGRAM FOR ADMIN

Dept of CSE SREC Page 22

 Identification Of Fake Profiles Using Artificial Neural Networks

4.4.1 User case Diagram for User:

FIG 4.4.1: USECASE DIAGRAM FOR USER

Dept of CSE SREC Page 23

 Identification Of Fake Profiles Using Artificial Neural Networks

4.5 SEQUENCE DIAGRAM:

A sequence diagram is a kind of interaction diagram that shows how processes operate with one
another and in what order. It is a construct of a Message Sequence Chart. A sequence diagram shows object
interactions arranged in time sequence. It depicts the objects and classes involved in the scenario and the
sequence of messages exchanged between the objects needed to carry out the functionality of the scenario.
Sequence diagrams are typically associated with use case realizations in the Logical View of the system
under development. Sequence diagrams are sometimes called event diagrams, event scenarios, and timing
diagrams.

Admin User Login Generate ANN View ANN Train Account Details Get Predicted Logout
Train Model Dataset Results

Login

Login Successfully

Generate ANN Train Model

Accuracy Displayed

View ANN Train Dataset

Dataset Details are displayed

Logout

Enter User Account Details

Get Predicted Details

Predicted Details are displayed

FIG 4.5: SEQUENCE DIAGRAM

Dept of CSE SREC Page 24

 Identification Of Fake Profiles Using Artificial Neural Networks

4.6 COLLABORATION DIAGRAM:

A collaboration diagram describes interactions among objects in terms of sequenced messages.
Collaboration diagrams represent a combination of information taken from class, sequence, and use case
diagrams describing both the static structure and dynamic behaviour of a system.

Login

2: Login Successfully

1: Login
3: Generate ANN Train Model
Generate ANN
6: Dataset Details are displayed Train Model
View ANN Trai Admin
n Dataset 4: Accuracy Displayed
5: View ANN Train Dataset

7: Logout

Account
Details
8: Enter User Account Details Logout

10: Predicted Details are displayed

Get Predicted User
Results
9: Get Predicted Details

FIG 4.6: COLLABORATION DIAGRAM

Dept of CSE SREC Page 25

 Identification Of Fake Profiles Using Artificial Neural Networks

4.7 COMPONENT DIAGRAM:

In the Unified Modelling Language, a component diagram depicts how components are wired together
to form larger components and or software systems. They are used to illustrate the structure of arbitrarily
complex systems. Components are wired together by using an assembly connector to connect the required
interface of one component with the provided interface of another component. This illustrates the service
consumer - service provider relationship between the two components.

FIG 4.7: COMPONENT DIAGRAM FOR ADMIN

Dept of CSE SREC Page 26

 Identification Of Fake Profiles Using Artificial Neural Networks

4.7.1 Component diagram for user:

FIG 4.7.1: COMPONENT DIAGRAM FOR USER

4.8 DEPLOYMENT DIAGRAM:

A deployment diagram in the Unified Modeling Language models the physical deployment of artifacts
on nodes. To describe a web site, for example, a deployment diagram would show what hardware
components ("nodes") exist (e.g., a web server, an application server, and a database server), what software
components ("artifacts") run on each node (e.g., web application, database), and how the different pieces are
connected (e.g., JDBC, REST, RMI). The nodes appear as boxes, and the artifacts allocated to each node
appear as rectangles within the boxes. Nodes may have sub nodes, which appear as nested boxes.

A single node in a deployment diagram may conceptually represent multiple physical nodes, such as a
cluster of database servers.

Dept of CSE SREC Page 27

 Identification Of Fake Profiles Using Artificial Neural Networks

Admin

System

User

FIG 4.8: DEPLOYMENT DIAGRAM

4.9 ACTIVITY DIAGRAM:

Activity diagram is another important diagram in UML to describe dynamic aspects of the system. It is
basically a flow chart to represent the flow form one activity to another activity. The activity can be
described as an operation of the system. So, the control flow is drawn from one operation to another. This
flow can be sequential, branched or concurrent.

FIG 4.9: ACTIVITY DIAGRAM FOR ADMIN

Dept of CSE SREC Page 28

 Identification Of Fake Profiles Using Artificial Neural Networks

Activity Diagram for User:

FIG 4.9.1: ACTIVITY DIAGRAM FOR USER

4.10 Dataflow Diagram:

Data flow diagrams illustrate how data is processed by a system in terms of inputs and outputs. Data
flow diagrams can be used to provide a clear representation of any business function. The technique starts
withan overall picture of the business and continues by analyzing each of the functional areas of interest.
This analysis can be carried out in precisely the level of detail required. The technique exploits a method
called top-down expansion to conduct the analysis in a targeted way.

As the name suggests, Data Flow Diagram (DFD) is an illustration that explicates the passage of
information in a process. A DFD can be easily drawn using simple symbols. Additionally, complicated
processes can be easily automated by creating DFDs using easy-to-use, free downloadable diagramming
tools. A DFD is a model for constructing and analyzing information processes. DFD illustrates the flow of
information in a process depending upon the inputs and outputs. A DFD can also be referred to as a Process
Model. A DFD demonstrates business or technical process with the support of the outside data saved, plus
the data flowing from the process to another and the end results.

Dept of CSE SREC Page 29

 Identification Of Fake Profiles Using Artificial Neural Networks

Fig 4.10: DATAFLOW DIAGRAM

Dept of CSE SREC Page 30

 Identification Of Fake Profiles Using Artificial Neural Networks

4.11 List of UML Notations:

SYMBOL
S.NO SYMBOL DESCRIPTION
NAME
1 Class Classes represent a collection of similar entities
grouped together.

2 Association Association represents a static relationship between

classes.

3 Aggregation Aggregation is a form of association. It aggregates

several classes into single class.

4 Actor Actors are the users of the system and other

external entity that react with the system.

Actor

5 Use Case A use case is an interaction between the system and

the external environment.

6 Relation (Uses) It is used for additional process communication.

Dept of CSE SREC Page 31

 Identification Of Fake Profiles Using Artificial Neural Networks

7 Communication It is the communication between various use cases.

8 State It represents the state of a process. Each state goes

through various flows.

9 Initial State It represents the initial state of the object.

10 Final State It represents the final state of the object.

11 Control Flow It represents the various control flow between the

states.

12 Decision Box It represents the decision making process from a

constraint.

13 Component Components represent the physical components

used in the system.

Component

14 Node Deployment diagrams use the nodes for

representing physical modules, which is a
Node
collection of components.

15 Data A circle in DFD represents a state or process which

Process/State has been triggered due to some event or action.

Dept of CSE SREC Page 32

 Identification Of Fake Profiles Using Artificial Neural Networks

16 External Entity It represents any external entity such as keyboard,

sensors etc.

17 Transition It represents any communication that occurs

between the processes.

18 Object Lifeline Object lifelines represents the vertical dimension

that objects communicate.

19 Message It represents the messages exchanged.

TABLE 4.11: UML NOTATIONS

Dept of CSE SREC Page 33

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER -5
IMPLEMENTATION
5.1 PYTHON:

Python is a general-purpose language. It has wide range of applications from Web development (like:
Django and Bottle), scientific and mathematical computing (Orange, SymPy, NumPy) to desktop graphical
user Interfaces (Pygame, Panda3D). The syntax of the language is clean and length of the code is relatively
short. It's fun to work in Python because it allows you to think about the problem rather than focusing on the
syntax.

History of Python: Python is a fairly old language created by Guido Van Rossum. The design began in the
late 1980s and was first released in February 1991.

Why Python was created?

In late 1980s, Guido Van Rossum was working on the Amoeba distributed operating system group. He
wanted to use an interpreted language like ABC (ABC has simple easy-to-understand syntax) that could
access the Amoeba system calls. So, he decided to create a language that was extensible. This led to design
of a new language which was later named Python.

Why the name Python?

No. It wasn't named after a dangerous snake. Rossum was fan of a comedy series from late seventies.
The name "Python" was adopted from the same series "Monty Python's Flying Circus".

Features of Python:

1. A simple language which is easier to learn: Python has a very simple and elegant syntax. It's much
easierto read and write Python programs compared to other languages like: C++, Java, C#. Python makes
programming fun and allows you to focus on the solution rather than syntax.If you are a newbie, it's a great
choice to start your journey with Python.

2. Free and open-source: You can freely use and distribute Python, even for commercial use. Not only can
you use and distribute software’s written in it, you can even make changes to the Python's source code.
Python has a large community constantly improving it in each iteration.

Dept of CSE SREC Page 34

 Identification Of Fake Profiles Using Artificial Neural Networks

3. Portability: You can move Python programs from one platform to another, and run it without any
changes.It runs seamlessly on almost all platforms including Windows, Mac OS X and Linux.

4. Extensible and Embeddable: Suppose an application requires high performance. You can easily
combine pieces of C/C++ or other languages with Python code. This will give your application high
performance as well as scripting capabilities which other languages may not provide out of the box.

5. A high-level, interpreted language: Unlike C/C++, you don't have to worry about daunting tasks like
memory management, garbage collection and so on. Likewise, when you run Python code, it automatically
converts your code to the language your computer understands. You don't need to worry about any lower-
level operations.

6. Large standard libraries to solve common tasks: Python has a number of standard libraries which
makes life of a programmer much easier since you don't have to write all the code yourself. For example:
Need to connect MySQL database on a Web server? You can use MySQL Db library using import MySQL
db. Standard libraries in Python are well tested and used by hundreds of people. So you can be sure that it
won't break your application.

7. Object-oriented: Everything in Python is an object. Object oriented programming (OOP) helps you solve
a complex problem intuitively. With OOP, you are able to divide these complex problems into smaller sets
by creating objects.

Applications of Python:

1. Simple Elegant Syntax: Programming in Python is fun. It's easier to understand and write Python code.
Why? The syntax feels natural. Take this source code for an example:

a=2

b=3

sum = a + b

print(sum)

2. Not overly strict: You don't need to define the type of a variable in Python. Also, it's not necessary to add
semicolon at the end of the statement. Python enforces you to follow good practices (like proper
indentation). These small things can make learning much easier for beginners.

Dept of CSE SREC Page 35

 Identification Of Fake Profiles Using Artificial Neural Networks

3. Expressiveness of the language: Python allows you to write programs having greater functionality with
fewer lines of code. Here's a link to the source code of Tic-tac-toe game with a graphical interface and a
smart computer opponent in less than 500 lines of code. This is just an example. You will be amazed how
much you can do with Python once you learn the basics.

4. Great Community and Support: Python has a large supporting community. There are numerous active
forums online which can be handy if you are stuck.

5.2 INTRODUCTION TO MACHINE LEARNING:

Machine learning (ML) is a field of inquiry devoted to understanding and building methods that ‘learn',
that is, methods that leverage data to improve performance on some set of tasks. It is seen as a part of
artificial intelligence Machine learning algorithms build a model based on sample data, known as training
data, in order to make predictions or decisions without being explicitly programmed to do so Machine
learning algorithms are used in a wide variety of applications, such as in medicine, email filtering, speech
recognition, agriculture, and computer vision, where it is difficult or unfeasible to develop conventional
algorithms to perform the needed tasks. A subset of machine learning is closely related to computational
statistics, which focuses on making predictions using computers, but not all machine learning is statistical
learning. The study of mathematical optimization delivers methods, theory and application domains to the
field of machine learning. Data mining is a related field of study, focusing on exploratory data analysis
through unsupervised learning. Some implementations of machine learning use data and neural networks in a
way that mimics the working of a biological brain. In its application across business problems, machine
learning is also referred to as predictive analytics.

FIG 5.2: MACHINE LEARNING PROCESS

Dept of CSE SREC Page 36

 Identification Of Fake Profiles Using Artificial Neural Networks

5.3 APPROACHES:

Supervised Learning: The computer is presented with example inputs and their desired outputs, given by a
"teacher", and the goal is to learn a general rule that maps inputs to outputs.

Unsupervised learning: No labels are given to the learning algorithm, leaving it on its own to find structure
in its input. Unsupervised learning can be a goal in itself (discovering hidden patterns in data) or a means
towards an end (feature learning).

Reinforcement learning: A computer program interacts with a dynamic environment in which it must
perform a certain goal (such as driving a vehicle or playing a game against an opponent). As it navigates its
problem space, the program is provided feedback that's analogous to rewards, which it tries to maximize.

5.4 USE OF ANN ALGORITHM:

ANN stands for Artificial Neural Network. It is a machine learning algorithm that is designed to
simulate the behavior of the human brain. The basic idea behind an ANN is to use a network of artificial
neurons that are interconnected to perform a specific task. The depth of an Artificial Neural Network (ANN)
refers to the number of hidden layers it has. A simple neural network with no hidden layers is called a
perceptron, and it has a depth of 0. However, most ANNs have multiple hidden layers, which enables them
to learn complex patterns and relationships in the input data.

The depth of an ANN plays a crucial role in its ability to learn and generalize. A shallow network with
only one or two hidden layers may not be able to capture complex patterns in the input data. On the other
hand, a deep network with many hidden layers may be able to learn more intricate and abstract features of
the input data. However, deeper networks are also more difficult to train, as the gradients used to update the
weights and biases of the neurons can become very small or very large, leading to the problem of vanishing
or exploding gradients. This can result in slower convergence or even prevent the network from converging
altogether.

To overcome this challenge, several techniques have been developed to improve the training of
deepnetworks, such as using better initialization schemes, regularization methods, and activation functions.
Additionally, the use of pre-trained deep networks, which have already learned features from large amounts
of data, has become popular in many applications.

Dept of CSE SREC Page 37

 Identification Of Fake Profiles Using Artificial Neural Networks

Overall, the depth of an ANN is an important factor to consider when designing a neural network
architecture. A deeper network can potentially lead to better performance, but it requires careful training and
parameter tuning to achieve optimal results.

FIG 5.4: PROCESS OF ANN ALGORITHM

Here is a step-by-step explanation of how an ANN works:

1. Data Pre-processing: The first step in training an ANN is to preprocess the data. This includes
cleaning and formatting the data, removing outliers, and normalizing the data to ensure that all
features are on the same scale.

2. Building the Model: Next, we need to build the ANN model by defining the number of layers,
number of neurons in each layer, and the activation function for each neuron. The most common type
of ANN is a feed forward neural network, which means that the data flows in only one direction from
the input layer to the output layer.

3. Training the Model: Once the model is built, we need to train it using a training dataset. During
training, the weights and biases of the neurons are adjusted based on the error between the predicted
output and the actual output. This is done using an optimization algorithm such as gradient descent.

Dept of CSE SREC Page 38

 Identification Of Fake Profiles Using Artificial Neural Networks

4. Testing the Model: After the model is trained, we need to test it using a separate dataset to evaluate
its performance. This will give us an idea of how well the model can generalize to new data.

5. Tuning the Model: Finally, we can tune the model by adjusting its parameters such as the learning
rate, number of epochs, and the number of hidden layers. This is done to improve the performance of
the model on the test dataset.

Here are a few examples of how ANN can be used:

1. Image Classification: ANN can be used to classify images into different categories such as animals,
buildings, or vehicles. This can be useful in applications such as self-driving cars or surveillance
systems.

2. Predicting Stock Prices: ANN can be used to predict the stock prices of companies based on their
historical data. This can help investors make informed decisions about buying and selling stocks.

3. Medical Diagnosis: ANN can be used to diagnose medical conditions based on patient data such as
symptoms, test results, and medical history. This can help doctors make accurate diagnoses and
recommend appropriate treatments.

4. Language Translation: ANN can be used to translate text from one language to another. This can be
useful in applications such as online translation services or in international business communication.

5. Fraud Detection: ANN can be used to detect fraudulent transactions in financial systems. This can
help prevent financial losses and protect the interests of consumers and businesses alike.

EXAMPLE:

Input Layer Hidden Layer Output Layer

ooooo oooooo ooooo

\ / \ / / \

\/ \/ / \
o o o o

Dept of CSE SREC Page 39

 Identification Of Fake Profiles Using Artificial Neural Networks

In this example, we have an ANN with three layers: an input layer, a hidden layer, and an output layer.
The input layer consists of five neurons, which receive the input data. The hidden layer consists of six
neurons, which process the input data and generate an output. The output layer consists of two neurons,
which produce the final output.

The lines between the neurons represent the connections between them. Each connection has a
weight,which determines the strength of the connection. The circles represent the neurons, which apply an
activation function to the sum of the inputs they receive to produce their output.

Overall, this ANN takes the input data, processes it through the hidden layer, and produces an output
in the output layer. The weights and biases of the neurons are adjusted during training to improve the
accuracy of the model.

Applications:

Artificial Neural Networks (ANNs) have a wide range of applications in various fields. Here are some
examples of how ANNs are used:

1. Image and Speech Recognition: ANNs are widely used in image and speech recognition
applications. For example, convolutional neural networks (CNNs) are used for image recognition
tasks such as face recognition and object detection. Recurrent neural networks (RNNs) are used for
speech recognition tasks such as speech-to-text conversion.

2. Natural Language Processing: ANNs are used in natural language processing (NLP) tasks such as
language translation and sentiment analysis. For example, recurrent neural networks (RNNs) are used
for language translation tasks.

3. Financial Prediction: ANNs are used for financial prediction tasks such as stock price prediction
and credit risk assessment. For example, multilayer perceptron (MLP) neural networks are used for
stock price prediction.

4. Medical Diagnosis: ANNs are used for medical diagnosis tasks such as disease diagnosis and
medical imaging analysis. For example, convolutional neural networks (CNNs) are used for medical
imaging analysis tasks such as tumor detection.

Dept of CSE SREC Page 40

 Identification Of Fake Profiles Using Artificial Neural Networks

5. Autonomous Vehicles: ANNs are used in autonomous vehicles for tasks such as object detection,
lane detection, and obstacle avoidance. For example, convolutional neural networks (CNNs) are used
for object detection tasks in self-driving cars.

6. Robotics: ANNs are used in robotics for tasks such as object recognition, navigation, and control.
For example, reinforcement learning algorithms based on ANNs are used for robotic control tasks.

7. Marketing and Advertising: ANNs are used in marketing and advertising for tasks such as
customer segmentation and recommendation systems. For example, collaborative filtering algorithms
based on ANNs are used for recommendation systems.

Overall, ANNs are a powerful tool for solving complex problems in various fields, and their applications are
constantly expanding as the technology advances.

5.5 SAMPLE CODE:

Views.py:

from django.shortcuts import render

from django.template import RequestContext

from django.contrib import messages

from django.http import HttpResponse

import pandas as pd

from sklearn.model_selection import train_test_split

from keras.models import Sequential

from keras.layers.core import Dense,Activation,Dropout

from keras.callbacks import EarlyStopping

from sklearn.preprocessing import OneHotEncoder

from keras.optimizers import Adam

Dept of CSE SREC Page 41

 Identification Of Fake Profiles Using Artificial Neural Networks

global model

def index(request):

if request.method == 'GET':

return render(request, 'index.html', {})

def User(request):

if request.method == 'GET':

return render(request, 'User.html', {})

def Admin(request):

if request.method == 'GET':

return render(request, 'Admin.html', {})

def AdminLogin(request):

if request.method == 'POST':

username = request.POST.get('username', False)

password = request.POST.get('password', False)

if username == 'admin' and password == 'admin':

context= {'data':'welcome '+username}

return render(request, 'AdminScreen.html', context)

else:

context= {'data':'login failed'}

Dept of CSE SREC Page 42

 Identification Of Fake Profiles Using Artificial Neural Networks

return render(request, 'Admin.html', context)

def importdata():

balance_data = pd.read_csv('C:/FakeProfile/Profile/dataset/dataset.txt')

balance_data = balance_data.abs()

rows = balance_data.shape[0] # gives number of row count

cols = balance_data.shape[1] # gives number of col count

return balance_data

def splitdataset(balance_data):

X = balance_data.values[:, 0:8]

y_= balance_data.values[:, 8]

y_ = y_.reshape(-1, 1)

encoder = OneHotEncoder(sparse=False)

Y = encoder.fit_transform(y_)

print(Y)

train_x, test_x, train_y, test_y = train_test_split(X, Y, test_size=0.2)

return train_x, test_x, train_y, test_y

def UserCheck(request):

if request.method == 'POST':

data = request.POST.get('t1', False)

input='Account_Age,Gender,User_Age,Link_Desc,Status_Count,Friend_Count,Location,Location

_IP\n';input+=data+"\n"

f = open("C:/FakeProfile/Profile/dataset/test.txt", "w")

Dept of CSE SREC Page 43

 Identification Of Fake Profiles Using Artificial Neural Networks
f.write(input)

f.close()

test = pd.read_csv('C:/FakeProfile/Profile/dataset/test.txt')

test = test.values[:, 0:8]

predict = model.predict_classes(test)

print(predict[0])

msg = ''

if str(predict[0]) == '0':

msg = "Given Account Details Predicted As Genuine"

if str(predict[0]) == '1':

msg = "Given Account Details Predicted As Fake"

context= {'data':msg}

return render(request, 'User.html', context)

def GenerateModel(request):

global model

data = importdata()

train_x, test_x, train_y, test_y = splitdataset(data)

model = Sequential()

model.add(Dense(200, input_shape=(8,),

activation='relu', name='fc1'))

model.add(Dense(200, activation='relu',

Dept of CSE SREC Page 44

 Identification Of Fake Profiles Using Artificial Neural Networks

name='fc2')) model.add(Dense(2,

activation='softmax', name='output'))
optimizer = Adam(lr=0.001)

model.compile(optimizer, loss='categorical_crossentropy', metrics=['accuracy'])

print('CNN Neural Network Model Summary: ')

print(model.summary())

model.fit(train_x, train_y, verbose=2, batch_size=5, epochs=200)

results = model.evaluate(test_x, test_y)

ann_acc = results[1] * 100

context= {'data':'ANN Accuracy : '+str(ann_acc)}

return render(request, 'AdminScreen.html', context)

def ViewTrain(request):

if request.method == 'GET':

strdata = '<table border=1 align=center width=100%><tr><th><font size=4 color=white>Account

Age</th><th> <font size=4 color=white>Gender</th><th><font size=4 color=white>User
Age</th><th><font size=4 color=white>Link Description</th> <th><font size=4 color=white>Status
Count</th><th><fontsize=4color=white>FriendCount</th><th><fontsize=4color=white>Location</th><t>
<fontsize=4color=white>LocationIP</th><th><fontsize=4 color=white>Profile Status</th></tr><tr>'

data = pd.read_csv('C:/FakeProfile/Profile/dataset/dataset.txt')

rows = data.shape[0] # gives number of row count

cols = data.shape[1] # gives number of col count

for i in range(rows):

Dept of CSE SREC Page 45

 Identification Of Fake Profiles Using Artificial Neural Networks

for j in range(cols):

strdata+='<td><font size=3 color=white>'+str(data.iloc[i,j])+'</font></td>'

strdata+='</tr><tr>'

context= {'data':strdata}

return render(request, 'ViewData.html', context)

Dept of CSE SREC Page 46

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER - 6
IMPLEMENTATION & TESTING
Implementation is one of the most important tasks in project is the phase in which one has to be cautions
because all the efforts undertaken during the project will be very interactive. Implementation is the most
crucial stage in achieving successful system and giving the users confidence that the new system is workable
and effective. Each program is tested individually at the time of development using the sample data and has
verified that these programs link together in the way specified in the program specification. The computer
system and its environment are tested to the satisfaction of the user.

6.1 IMPLEMENTATION:

The implementation phase is less creative than system design. It is primarily concerned with user
training, and file conversion. The system may be requiring extensive user training. The initial parameters of
the system should be modifying as a result of a programming. A simple operating procedure is provided so
that the user can understand the different functions clearly and quickly. The different reports can be obtained
either on the inkjet or dot matrix printer, which is available at the disposal of the user. The proposed
system is very easy to implement. In general implementation is used to mean the process of converting a
new or revised system design into an operational one.

6.2 TESTING:

Testing is the process where the test data is prepared and is used for testing the modules individually
andlater the validation given for the fields. Then the system testing takes place which makes sure that all
components of the system property function as a unit. The test data should be chosen such that it passed
through all possible condition. Actually, testing is the state of implementation which aimed at ensuring that
the system works accurately and efficiently before the actual operation commence. The following is the
description of the testing strategies, which were carried out during the testing period.

6.3 SYSTEM TESTING:

Testing has become an integral part of any system or project especially in the field of information
technology. The importance of testing is a method of justifying, if one is ready to move further, be it to be
check if one is capable to with stand the rigors of a particular situation cannot be underplayed and that is
why testing before development is so critical. When the software is developed before it is given to user to
user the software must be tested whether it is solving the purpose for which it is developed.

Dept of CSE SREC Page 47

 Identification Of Fake Profiles Using Artificial Neural Networks

This testing involves various types through which one can ensure the software is reliable. The program
was tested logically and pattern of execution of the program for a set of data are repeated. Thus the code was
exhaustively checked for all possible correct data and the outcomes were also checked.

6.4 MODULE TESTING:

To locate errors, each module is tested individually. This enables us to detect error and correct it without
affecting any other modules. Whenever the program is not satisfying the required function, it must be
corrected to get the required result. Thus, all the modules are individually tested from bottom up starting
with the smallest and lowest modules and proceeding to the next level. Each module in the system is tested
separately. For example, the job classification module is tested separately. This module is tested with
different job and its approximate execution time and the result of the test is compared with the results that
are prepared manually. The comparison shows that the results proposed system works efficiently than the
existing system. Each module in the system is tested separately. In this system the resource classification and
job scheduling modules are tested separately and their corresponding results are obtained which reduces the
process waiting time.

6.5 INTEGRATION TESTING:

After the module testing, the integration testing is applied. When linking the modules there may be
chance for errors to occur, these errors are corrected by using this testing. In this system all modules are
connected and tested. The testing results are very correct. Thus, the mapping of jobs with resources is done
correctly bythe system.

6.6 ACCEPTANCE TESTING:

When that user fined no major problems with its accuracy, the system passers through a final
acceptance test. This test confirms that the system needs the original goals, objectives and requirements
established during analysis without actual execution which elimination wastage of time and money
acceptance tests on the shoulders of users and management, it is finally acceptable and ready for the
operation.

Dept of CSE SREC Page 48

 Identification Of Fake Profiles Using Artificial Neural Networks

Test Test Case Test Case Test Steps Test Test

Case Name Desc. Step Expected Actual Case Priority
Id Status
01 Admin Test whether If the Admin Admin Admin can High High
Login the admin is cannot enter cannot login login to the
login or not the valid to the system system
into the Details
system

02 generate Verify the Without login cannot ANN train High High
ANN train ANN train to the system generate the model
model model ANN train generated
generated or model successfully
not

03 view Verify the Without the ANN the ANN High High
ANN train ANN train generating the train Dataset train Dataset
Dataset Dataset training model details may details
displayed or not display displayed
not successfully
04 Checking Verify either Without we cannot account High High
User the user entering the find that predicted
Accounts account is user account account is details are
fake or details fake or displayed
genuine genuine successfully

TABLE 6.2: TESTCASES

Dept of CSE SREC Page 49

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER – 7
SCREENSHOT
7.1 HOME PAGE:
In above screen click on ‘ADMIN’ link to get below login screen

FIG 7.1: HOME PAGE

Dept of CSE SREC Page 50

 Identification Of Fake Profiles Using Artificial Neural Networks

7.2 ADMIN PAGE:

In above screen enter admin and admin as username and password to login as admin. After login
will getbelow screen.

FIG 7.2: ADMIN PAGE

Dept of CSE SREC Page 51

 Identification Of Fake Profiles Using Artificial Neural Networks

7.3 GENERATE ANN MODEL:

In above screen click on ‘Generate ANN Train Model’ to generate training model on dataset. After
clickingon that link, you can see server console to check ANN processing details with accuracy.

FIG 7.3: GENERATE ANN MODEL

Dept of CSE SREC Page 52

 Identification Of Fake Profiles Using Artificial Neural Networks

7.4 VIEW ANN TRAIN MODEL:

In above black console we can see all ANN details.

FIG 7.4: VIEW ANN TRAIN MODEL

Dept of CSE SREC Page 53

 Identification Of Fake Profiles Using Artificial Neural Networks

7.5 ANN ACCURACY:

In above screen we can see ANN got 98% accuracy to train all Facebook profile. Now click on ‘View
AnnTrain Dataset’ link to view all dataset details.

FIG 7.5: ANN ACCURACY TRAIN PAGE

Dept of CSE SREC Page 54

 Identification Of Fake Profiles Using Artificial Neural Networks

7.5.1 : All Train Data and Records:

FIG 7.5.1: ALL TRAIN DATA AND RECORDS

In above screen we can see all train data and scroll down to view all records. Now ANN train model is
readyand you can logout and click on ‘User’ link to get below screen.

Dept of CSE SREC Page 55

 Identification Of Fake Profiles Using Artificial Neural Networks

7.6 USER PAGE:

In above screen enter some test account details to get prediction/identification from ANN. You can
usebelow records to check.

FIG 7.6: USER ACCOUNT CHECK

Dept of CSE SREC Page 56

 Identification Of Fake Profiles Using Artificial Neural Networks

7.7 TEXT DATA ATTRIBUTE VALUES:

10,1,44,0,280,1273,0, 0
10,0,54,0,5237,241,0,0
7,0,42,1,57,631,1,1
7,1,56,1,66,623,1,1

FIG 7.7: USER ACCOUNT TO TEXT THE DATA VALUE ATTRIBUTES

Dept of CSE SREC Page 57

 Identification Of Fake Profiles Using Artificial Neural Networks

7.7.1 : Account Details Predicted as Fake or Genuine:

FIG 7.7.1: ACCOUNT DETAILS PREDICTED AS FAKE OR GENIUNE

Dept of CSE SREC Page 58

 Identification Of Fake Profiles Using Artificial Neural Networks

7.7.2 : Sample 1 Data to Test Genuine or Fake:

FIG 7.7.2: SAMPLE 1 DATA TO TEST GENIUNE OR FAKE

Dept of CSE SREC Page 59

 Identification Of Fake Profiles Using Artificial Neural Networks

7.7.3 : Sample 2 Data to Test Genuine Or Fake:

FIG 7.7.3: SAMPLE 2 DATA TO TEST GENIUNE OR FAKE

Output: In above screen we got result as fake for given account data.

Dept of CSE SREC Page 60

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER – 8
CONCLUSION
In this project, we use machine learning, namely an artificial neural network to determine what are the
chances that a friend request is authentic are or not. Each equation at each neuron (node) is put through a
Sigmoid function. We use education records set by using Facebook or different social networks. This would
enable the introduced deep gaining knowledge of algorithm We use a training data set by Facebook or other
social networks. This would allow the presented deep learning algorithm to learn the patterns of bot
behaviour by back propagation, minimizing the final cost function and adjusting each neuron's weight and
bias. In this project, we outline the classes and libraries involved. We also discuss the sigmoid function and
how are the weights determined and used. We also consider the parameters of the social network page which
are the most important to our solution. The typical social media user is unaware that they are waiving certain
legal protections by using the site. To the detriment of its users, social media platforms stand to gain a great
deal. The purpose of this project is to utilize machine learning, specifically an artificial neural network, to
predict whether the friend request is genuine or not in social media platforms.

Dept of CSE SREC Page 61

 Identification Of Fake Profiles Using Artificial Neural Networks

CHAPTER – 9
REFERENCES
1. https://www.statista.com/topics/1164/social-networks

2. https://www.cnbc.com/2018/01/31/facebook-earnings-q4-2017- arpu.html

3. https://www.cnet.com/news/facebook-breach-affected-50-millionpeople/

4. https://www.facebook.com/policy.php

5. Qiang Cao, Michael Sirivianos, Xiaowei Yang, and Tiago Pregueiro. 2012. Aiding the detection of fake
accounts in large scale social online services. In Proceedings of the 9th USENIX conference on Networked
Systems Design and Implementation (NSDI'12). USENIX Association, Berkeley, CA, USA, 15-15.

6. Akshay J. Sarode and Arun Mishra. 2015. Audit and Analysis of Impostors: An experimental approach to
detect fake profile in an online social network. In Proceedings of the Sixth International Conference on
Computer and Communication Technology 2015 (ICCCT '15). ACM, New York, NY, USA, 1-8. DOI:
https://doi.org/10.1145/2818567.2818568

7. Devakunchari Ramalingam, Valliyammai Chinnaiah. Fake profile detection techniques in large-scale

online social networks: A comprehensive review. Computers & Electrical Engineering, Volume65, 2018,
pages 165-177, ISSN 0045-7906

8. https://www.enigmasoftware.com/top-20-countries-the-most-cybercrime

9. pages.cs.wisc.edu/~bolo/shipyard/neural/local.html

10. https://stackoverflow.com/questions/40758562/can-anyone-explain-mestandardscaler

11. https://doi.org/10.1016/j.compeleceng.2017.05.020.

Dept of CSE SREC Page 62

 nternational Journal of Research Publication and Reviews, Vol 4, no 4, pp 1563-1566, April 2023

International Journal of Research Publication and Reviews

Journal homepage: www.ijrpr.com ISSN 2582-7421

An Attempt at Detecting Fake Profiles Using Neural Networks

Mr.M.Amareswara Kumar1, G.Manjulatha2,A.Srivalli3,M.Shabhirun4,B.Ramani5,C.Bhavani6

1
Assistant Professor, Department of Computer Science and Engineering, Santhiram Engineering College, Nandyal
2,3,4,5,6
Department of Computer Science and Engineering, Santhiram Engineering College, Nandyal
DOI: https://doi.org/10.55248/gengpi.2023.4.4.35591

ABSTRACT

Here, we use machine learning, in the form of an artificial neural network, to calculate the probability that a user's friend request on Face book is genuine/real or
not. The relevant libraries and classes are also described. Further, we talk about the sigmoid function and how the weights are calculated and applied. In the end,
we think about the most crucial aspects of the social network page to consider while implementing the proposed solution.

Keywords: Neural Network,Social network analysis,Data Preprocessing.

I. INTRODUCTION

With 2.46 billion active users as of 2017, Facebook is clearly the most popular social media platform. The information shared by its users is the source
of income for social media platforms. When people sign up for a social media account, they don't realize that they're giving up certain legal protections.
The social media giants stand to earn significantly, but this comes at the price of the user.Facebook generates income from adverts and user data every
each time a person publishes information about their location, uploads a picture, expresses an,opinion about a post, or tags other users in a post user.
When you consider millions of users, that sum soon grows. The victims of a data breach may not even be aware that they were attacked[16]. Right now,
there is nothing driving social media platforms to beef up their data protection measures. These hacks often affect popular social media websites like
Facebook and Twitter. Every day, there's a new story about a social media platform that's been hacked. About 50 million individuals had their
information compromised recently on Facebook[12].

Facebook has a series of spelled-out policies that detail how the company handles userinformation . The policy doesn't do anything to stop the
persistent breaching of security and privacy. Unfortunately, it seems that Facebook's anti-fake profile measures often fail to catch the fake accounts that
are created. The proliferation of bots and phony accounts also increases the risk of personal data being collected for illicit reasons. The term "web
scraping" describes this action[17]. To make matters worse, this is well within the law. To steal personal information, bots might lurk undetected or
pose as a friend request on social networking sites.

This paper's proposed solution is meant to draw attention to the threats posed by a bot in the guise of a false social media presence. This answer would
be expressed in the form of an algorithm. Python is the programming language of choice for us[18].

As soon as a user receives a friend request online, the algorithm would be able to tell whether it was sent by a real person, a bot, or a phony account
trying to steal their personal information[13]. Our algorithm relies on the cooperation of the social media platforms, since we require a training dataset
provided by them in order to properly calibrate our model and then test it to see whether the profiles are genuine[11]. The algorithm may also function
in the conventional sense as a browser add-on for the user's web browser.

II. RELATED WORK

“Audit and Analysis of Imposters: A Novel Strategy for Identifying Fake Profiles in Social Networks.”

Nowadays, everyone's social life revolves on their many online social networks (OSN). The way we communicate with one another has been
revolutionized by these platforms. It is simpler to meet new people, maintain relationships with those you already have, and stay abreast of their latest
exploits. However, along with their meteoric rise, issues like bogus profiles and online impersonation have multiplied in number as well. The fact that
anybody may create a fake profile and pose as someone else poses a threat on the OSN[15].

In this work, we provide an experimental framework that makes fraudulent profile identification in a friend list possible, however it is only applicable
to the social networking site Facebook.

“An in-depth look at the methods used to spot fake profiles on the web's largest social networks”
 International Journal of Research Publication and Reviews, Vol 4, no 4, pp 1563-1566 April 2023 1564

Present day, the Internet's most widely used and rapidly spreading applications are online social networks.

Because of these incentives, fraudulent actors have begun preying on those who utilize social networks[16].

If you want to do the most damage on a social network, create a false profile and use it to spread fake news or other malicious content. As soon as a
phony profile is created, the user has to be alerted, but this crime needs to be uncovered far before that happens. The identification of false profiles has
been the subject of several algorithms and methodologies, many of which make advantage of the massive amount of unstructured data produced by
social networks[14].

This research provides an overview of the current and most recent technological progress on detecting bogus profiles.

III. METHODOLOGY

To assess the legitimacy of a friend request, we use machine learning, in the form of a synthetic neural network. An associated sigmoid function is
applied to each equation at each neuron (node) to ensure that the node-level solutions remain within the range [0.0, 1.0].

Multiplying this by 100 at the output end would give us the likely percentage that this is a malicious request. When it comes to our proposed approach,
we'll just be using a single deep neural network, which will have only one hidden layer. Each input neuron would be a different feature of each profile
that was selected in advance and converted into a numerical value (for example, gender as a binary number, female 0 and male 1) and, if necessary,
divided by an arbitrary number (for example, age is always divided by 100) to reduce the impact of any one feature. Nodes are represented by the
neurons. In this setup, each node would be in charge of making a single choice. Each factor contributes its own unique importance and perspective to
the equation. The calculated result would be a % estimate of how likely it is that the friend request is not from a genuine person. The used neural
network is shown in Fig. 1.

Fig.1:Neural Network

We need a training set, which may come from Facebook or another social media network site, or even simply web scraping if we locate enough phony
accounts.

Our deep learning system may then learn the bot's behavior patterns through back propagation by minimizing the final cost function and fine-tuning the
weights and biases of each neuron.

This article provides an overview of the related classes and libraries.

IV. RESULT AND DISCUSSION

In this study, we employ Artificial Neural Networks to determine whether the provided account data belong to real people or bots. The ANN algorithm
will be trained using both real and fraudulent account data from prior users, and then the ANN train model will be used to fresh test data to determine
whether the data represents real or fake accounts.

Fig.2: AdminPage
 International Journal of Research Publication and Reviews, Vol 4, no 4, pp 1563-1566 April 2023 1565

Enter your username and password to access the admin panel, and then use the ANN algorithm to train the dataset. The whole ANN profile is shown on
the rear control panel. Evidently,ANN was able to train every Facebook profile to an accuracy of 98%

Fig.3: Sample 1 Data To Test Geniune Or Fake

There is evidence to suggest this is a legitimate narrative. InFig. 3. sample 1 data result is genuine.

Fig.4: Sample 2 Data To Test Geniune or Fake

It's likely that this account is a hoax. In Fig.4 sample 2 data result is fake

V. CONCLUSION

Whether you get a friend request and you're not sure if it's real or not, run it through a neural network. For each neuron (node), the equations are
Sigmoid-transformed.

The data used for training comes from Facebook or another social network. The described deep learning method might then use back propagation to
learn the patterns of bot behaviour by optimizing the final cost function and fine-tuning the weights and biases of each neuron. This article provides an
overview of the related classes and libraries. We also talk about the sigmoid function and how the weights are calculated and applied for it. Important to
our solution are the characteristics of the social media page itself, which we take into account.

VI. REFERENCES

[1]https://www.statista.com/topics/1164/social-networks/

[2]https://www.cnbc.com/2018/01/31/facebook-earnings-q4-2017- arpu.html

[3]https://www.cnet.com/news/facebook-breach-affected-50-millionpeople/

[4] https://www.facebook.com/policy.php

[5] Qiang Cao, Michael Sirivianos, Xiaowei Yang, and Tiago Pregueiro. 2012. Aiding the detection of fake accounts in large scale social online
services. In Proceedings of the 9th USENIX conference on Networked Systems Design and Implementation (NSDI'12). USENIX Association,
Berkeley, CA, USA, 15-15.

[6] Akshay J. Sarode and Arun Mishra. 2015. Audit and Analysis of Impostors: An experimental approach to detect fake profile in an online social
network. In Proceedings of the Sixth International Conference on Computer and Communication Technology 2015 (ICCCT '15). ACM, New York,
NY, USA,1-8.DOI: https://doi.org/10.1145/2818567.2818568

[7] Devakunchari Ramalingam, ValliyammaiChinnaiah. Fake profile detection techniques in large-scale online social networks: A comprehensive
review. Computers & Electrical Engineering, Volume 65, 2018, Pages 165-177, ISSN 0045-7906, https://doi.org/10.1016/j.compeleceng.2017.05.020.

[8] https://www.enigmasoftware.com/top-20-countries-the-most-cybercrime
 International Journal of Research Publication and Reviews, Vol 4, no 4, pp 1563-1566 April 2023 1566

[9]pages.cs.wisc.edu/~bolo/shipyard/neural/local.html

[10]https://stackoverflow.com/questions/40758562/can-anyone-explain-mestandardscaler

[11] Karukula, Nageswara Reddy, and Sunar Mohammed Farooq. "A route map for detecting Sybil attacks in urban vehicular networks." Journal of
Information, Knowledge, and Research in Computer Engineering 2.2 (2013): 540-544.

[12] Mahammad, Farooq Sunar, and V. Madhu Viswanatham. "Performance analysis of data compression algorithms for heterogeneous architecture
through parallel approach." The Journal of Supercomputing 76.4 (2020): 2275-2288.

[13] Farooq, Sunar Mohammed, and K. NageswaraReddy. "Implementation of Intrusion Detection Systems for High Performance Computing
Environment Applications." (2015).

[14]Sathish, A., et al. "A Technique to Reduce Data-Bus Coupling Transitions in DSM Technology." i-Manager's Journal on Software Engineering 4.2
(2009): 67.

[15]Mallikarjuna Rao, Y., M. V. Subramanyam, and K. Satya Prasad. "Cluster‐ based mobility management algorithms for wireless mesh
networks." International Journal of Communication Systems 31.11 (2018): e3595.

[16]Subramanyam, M. V., and K. Satya Prasad. "Delay efficient algorithm for adhoc wireless networks." Information Technology Journal 5.5 (2006):
976-981.

[17]https://ijrar.org/papers/IJRAR19J2281.pdf

[18]https://www.ijrpr.com/uploads/V1ISSUE1/IJRPR0012.pdf

[19] Mahammad, Farooq Sunar, et al. "Prediction Of Covid-19 Infection Based on Lifestyle Habits Employing Random Forest Algorithm." JOURNAL
OF ALGEBRAIC STATISTICS 13.3 (2022): 40-45.

[20]https://ejmcm.com/article_9974_b564072310db5c6f9d1f5b39221afc09.pdf
 International Journal of Research
Publication and Reviews
(Open Access, Peer Reviewed, International Journal)
(A+ Grade, Impact Factor 5.536)
ISSN 2582-7421 Sr. No: IJRPR 23187

Certificate of Acceptance & Publication

This certificate is awarded to Mr. M. Amareswara

Kumaramar.cse@srecnandyal.edu.in, and certifies the acceptance for
publication of research paper entitled “An Attempt at Detecting Fake Profiles
Using Neural Networks” in “International Journal of Research Publication and
Reviews”, Volume 4, Issue 4, 2023.

Signed Date 11/04/2023

Editor-in-Chief
International Journal of Research Publication and Reviews
 International Journal of Research
Publication and Reviews
(Open Access, Peer Reviewed, International Journal)
(A+ Grade, Impact Factor 5.536)
ISSN 2582-7421 Sr. No: IJRPR 23191

Certificate of Acceptance & Publication

This certificate is awarded to B. Ramani, and certifies the acceptance for

publication of research paper entitled “An Attempt at Detecting Fake Profiles
Using Neural Networks” in “International Journal of Research Publication and
Reviews”, Volume 4, Issue 4, 2023.

Signed Date 11/04/2023

Editor-in-Chief
International Journal of Research Publication and Reviews