lOMoAR cPSD| 54161706

INDEX

Sr.no Contents Page No.

1 Abstract 1

2 Introduction 2-3

3 Main Details 4-17

4 Conclusion 18

5 Reference 18
 lOMoAR cPSD| 54161706

ABSTRACT

Social networks have become popular due to the ability to

connect people around the world and share videos, photos, and
communications. One of the security challenges in these
networks, which have become a major concern for users, is
creating fake accounts. In this paper, a new model which is
based on similarity between the users‟ friends‟ networks was
proposed in order to discover fake accounts in social networks.
Similarity measures such as common friends, cosine, Jaccard,
L1-measure, and weight similarity were calculated from the
adjacency matrix of the corresponding graph of the social
network. To evaluate the proposed model, all steps were
implemented on the Twitter dataset. The social network, a
crucial part of our life is plagued by online impersonation and
fake accounts. According to the
„Community Standards Enforcement Report‟ published by
Facebook on March 2018, about 583 million fake accounts
were taken down just in quarter 1 of 2018 and as many as 3-4%
of its active accounts during this time were still fake. The
community of concern to us here is Fake Accounts and our
problem can be said to be a classification or a clustering
problem.
 lOMoAR cPSD| 54161706

INTRODUCTION
In the present generation, the social life of everyone has
become associated with the online social networks. Adding new
friends and keeping in contact with them and their updates has
become easier. The online social networks have impact on the
science, education, grassroots organizing, employment,
business, etc. Researchers have been studying these online
social networks to see the impact they make on the people.
Teachers can reach the students easily through this making a
friendly environment for the students to study, teachers
nowadays are getting themselves familiar to these sites bringing
online classroom pages, giving homework, making discussions,
etc. which improves education a lot. The employers can use
these social networking sites to employ the people who are
talented and interested in the work, their background check can
be done easily.
The use of social networks such as Facebook, Twitter,
Google+, Instagram, and LinkedIn is on the rise. Individuals
and organizations use social networks to express their views,
advertise their products, and express future policies of their
companies and organizations. By expanding the use of social
networks, malicious users seek to violate the privacy of other
users and abuse their names and credentials by creating fake
accounts, which has become a concern for users. Hence, social
networks providers are trying to detect malicious users and fake
accounts in order to eliminate them from social networking
environments. Creating fake accounts in social networks causes
more damage than any other cybercrime.
 lOMoAR cPSD| 54161706

Removing fake accounts has attracted the attention of

many researches; thus, extensive researches have been carried
out on the identification of fake accounts in social networks.
Different approaches are proposed in and to find fake accounts
based on attribute similarity, similarity of friend networks,
profile analysis for a time interval, and similarity of attribute
together with IP address.
 lOMoAR cPSD| 54161706

PROPOSED SYSTEM
The Application Domain of the following project was
Community Detection. Community detection is key to
understanding the structure of complex networks, and
ultimately extracting useful information from them. In this
project, we came up with a framework through which we can
detect a fake profile using machine learning algorithms so that
the social life of people become secured.

1. Classification starts from the selection of profile that needs to

be classified.
2. Oncethe profile is selected, the useful features are extracted for
the purpose of classification.
3. The extracted features are then fed to trained classifier.
4. Classifier is trained regularly as new data is fed into the
classifier.
5. Classifier then determines whether the profile is genuine or
fake.
6. Theresult of classification algorithm is then verified and
feedback is fed back into the classifier.
7. As
the number of training data increases the classifier becomes
more and more accurate in predicting the fake profiles.
 lOMoAR cPSD| 54161706

ADVANTAGES
The social networking sites are making our social lives better
but nevertheless there are a lot of issues with using these
social networking sites.The issues are privacy, online
bullying, potential for misuse, trolling, etc. These are done
mostly by using fake profiles. In this project, we came up with
a framework through which we can detect a fake profile using
machine learning algorithms so that the social life of people
become secured.

DISADVANTAGES
Because of Privacy Issues the Facebook dataset is very limited
and a lot of details are not made public.

What is Cyber Security?

Cyber Security is the process and techniques involved in
protecting sensitive data, computer systems, networks and
software applications from cyber attacks. The cyber attacks are
general terminology which covers a large number of topics, but
some of the popular are:

i. Tampering systems and data stored within ii.

Exploitation of resources iii. Unauthorized access to
the targeted system and accessing sensitive information
iv. Disrupting normal functioning of the business and its
processes
 lOMoAR cPSD| 54161706

v. Using ransomware attacks to encrypt data and extort money

from victims

The attacks are now becoming more innovative and

sophisticated that is capable of disrupting the security and
hacking the systems. So it‟s very challenging for every
business and security analyst to overcome this challenge and
fight back with these attacks.

IMPROVING CYBER SECURITY

Cyber security is a constantly changing area and sometimes can
seem quite confusing. However, there are many effective and
relatively simple steps that can be taken to protect information
and protect you and your organisation. Taking some simple
actions and practising safe behaviours will reduce online
threats.

BACK UP YOUR DATA

If your device is infected by a virus or accessed by a hacker,
your data may be damaged, deleted, stolen or even held to
ransom, which means you won‟t be able to access it.You should
therefore safeguard your most important data by backing up to
a secure external hard drive or storage system based in the
Cloud.You should also ensure you regularly test your
back-ups and, if you are saving confidential data off-site e.g.
the Cloud, follow all appropriate data protection measures and
government standards and guidance that relate to health and
social care organisations.
For more information, please click here.
 lOMoAR cPSD| 54161706

IMPORTANCE OF CYBER SECURITY

Why is Cyber Security Awareness Important?
Advanced technologies have changed the modern way of life.
The internet provides us with many benefits. Be it
communicating with friends, searching for information, doing
banking transactions, availing online services, finding job,
finding life partner or even running entire businesses. The
internet touches almost all aspects of our lives. However, it also
makes us vulnerable to a wide range of threats.
New and powerful cyber-attacks are striking the internet
regularly. A minor lapse in managing our digital lives can open
the door to cyber criminals. Cyber criminals can steal our
money or damage our reputation. According to a study by a
leading industry research organization, 90% of all cyberattacks
are caused by human negligence. Therefore, cyber security
awareness is important for everyone today.
We must be vigilant while making use of technology to reduce
the risk of cyber threats.
Types of Cybercrime
A cybercrime is a crime involving computers and networks.
This includes a wide range of activities, from illegally
downloading music files to stealing money from online bank
accounts. Cyber criminals are not always financially motivated.
Cybercrimes include nonmonetary offenses as well. It can
include frauds such as job related frauds, matrimonial frauds;
 lOMoAR cPSD| 54161706

stealing and misusing sensitive personal information (Aadhaar

details, credit/debit card details, bank account credentials, etc.);
defamation of an individual on social media; distribution of
computer viruses etc. Cybercrimes can also lead to physical or
sexual abuse. In this booklet, we will discuss following
common types of cybercrimes prevalent today.

 Identity Theft
 Digital Banking Frauds
 Psychological Tricks
 Attacks through Mobile Applications
 Social Media related Attacks
 Virus Attacks onPersonal Computer

IDENTITY THEFT
What is Identity Theft?
Identity theft is the act of wrongfully obtaining someone‟s
personal information (that defines one‟s identity) without their
permission. The personal information may include their name,
phone number, address, bank account number, Aadhaar number
or credit/debit card number etc.Identity theft can have many
adverse effects. The fraudster can use stolen personal
information and identity proofs to:
• gain access to your bank accounts
• apply for loans and credit cards or open insurance
accounts
• file a tax refund in your name and get your refund
 lOMoAR cPSD| 54161706

• obtain a driver‟s license, passport or immigration papers

• create new utility accounts

• get medical treatment on your health insurance

• assume your identity on social media

• give your name to the police during an arrest etc.

Hence, everyone should be aware about identity theft and

should know how to prevent it. Let us look at some examples
of identity theft.
Hacking or gaining access to Social Media Accounts
The attacker hacks or gains access to the social media account
of the victim. The attacker can then harm the victim by
misusing their personal information and photographs. The
attacker can also post offensive content on victim‟s profile or
defame the victim.
Misuse of photo copies of identity proofs
The attacker misuses the photo copies of identity proofs of the
victim. These can be PAN Card, Aadhaar Card or any other
identity proof of the victim. The attacker can use these photo
copies to steal money or cause harm to the victim.
Credit/Debit Card Skimming
Credit/Debit card skimming is done using a small device called
skimmer. The magnetic stripe of the card stores details such as
name, credit/debit card number and expiration date. First, the
credit/debit card is swiped through a skimmer. Then, the
skimmer captures all these details. Thieves use this stolen data
 lOMoAR cPSD| 54161706

to make online transactions. They also use this data to create

duplicate credit/debit cards and withdraw money from ATM

SOCIAL MEDIA FRAUDS

What are Social Media Frauds?
Social Media has become an integral part of our lives. It is the
new way of communicating, sharing and informing people
about the events in our lives. We share our day to day lives on
social media in the form of self and family photographs,
updates on our locations/whereabouts, our views/thoughts on
prevalent topics etc. One can understand the entire history of
an individual through their social media profile and can even
predict future events based on patterns in the past.
This poses a threat to an individual as unwanted access to social
media profile can cause loss of information, defamation or
even worse consequences such as physical/sexual assault,
robbery etc. Hence, protection and appropriate use of social
media profile is very important.
Let us look at some examples of social media frauds. Sympathy
Fraud The attacker becomes friends with the victim on social
media. The attacker gains trust by frequent interactions. The
attacker later extracts money/harms the victim.
Romance Fraud
The attacker becomes friends with the victim on social media.
Over a period, the attacker gains victim‟s affection. The
attacker later exploits the victim physically, financially and/or
emotional .
Cyber Stalking
Cyber stalking is a crime in which the attacker harasses a victim
using electronic communication, such as e-mail, instant
messaging (IM), messages posted on a website or a discussion
group. A cyber stalker relies upon the fact that his/her true
identity is not known in the digital world. A cyber stalker targets
the victim with threatening/abusive messages and follows
them/their activities in the real world.
Cyber Bullying
Cyber bullying is bullying that takes place over digital devices.
Cyber bullying can occur through SMS, social media, forums
or gaming apps where people can view, participate or share
content. Cyber bullying includes sending, posting or sharing
negative, harmful, false content about someone else. The
intention is to cause embarrassment or humiliation. At times, it
can also cross the line into unlawful criminal behavior.
MOBILE APPLICATION FRAUDS
How mobile applications can be used for cyber frauds?
With the increase in the use of smartphones and the consequent
rise in the use of mobile applications, associated security risks
have also increased. The number of mobile transactions has
increased four times in the last couple of years, and now, cyber
criminals are targeting mobile users to extract data and money.
Mobile applications are widely used not only for entertainment
but also for ease and convenience to perform day-to-day tasks
such as bill payments, bank accounts management, service
delivery etc. As a result, these applications are more prone to
cyber-attacks. Users need to be aware of such attacks on
commonly used mobile applications such as digital payment
applications and gaming applications.
Let us look at some day to day example on how mobile
applications can be used for cyber frauds.

Cyber-attacks using Infected Mobile Applications

People become habitual users of certain mobile applications. As
a result, they ignore security warnings. Fraudsters use this to
attack the victim by infiltrating through such popular mobile
applications. They infect the applications with malicious
software, called Trojan. This Trojan can get access to your
messages, OTP, camera, contacts, e-mails, photos etc. for
malicious activities. It can also show obscene advertisements,
sign users up for paid subscriptions or steal personal sensitive
information from the mobile etc.

PSYCHOLOGICAL TRICKS
What are Psychological Tricks?
Psychological tricks are where attackers play with the minds of
the user to trap them with lucrative offers. Once trapped, the
attackers can exploit the victim by either stealing money or
stealing sensitive personal information (name, Aadhaar details,
bank account details etc.) or harm the victim in any other way.
The entire basis of this kind of attack is to make the victim fall
into their trap by sending fake e-mails, calls or SMSs.
Phishing is the act of sending fraudulent e-mail that appears to
be from a legitimate source, for example, a bank, a recruiter or
a credit card company etc. This is done in an attempt to gain
sensitive personal information, bank account details etc. from
the victim.
Vishing is similar to phishing. But, instead of e-mail, in this
type of crime, the fraudster uses telephone to obtain sensitive
personal and financial information.
Smishing is the SMS equivalent of phishing. It uses SMS to
send fraudulent text messages. The SMS asks the recipient to
visit a website/weblink or call a phone number. The victim is
then tricked into providing sensitive personal information,
debit/credit card details or passwords etc.
Phishing, Vishing and Smishing are done in an attempt to steal
money from the victim or cause any other harm to the victim.
Let us look at some examples of psychological tricks.
Lottery Fraud
The fraudster congratulates the victim for winning a handsome
lottery via e-mail/call/SMS. The victim is delighted and is eager
to get the lottery money. The fraudster asks the victim to
transfer a token amount and share vital personal information to
get the lottery money. The victim loses his/her money and does
not get anything in return.
Credit/Debit Card Fraud
The attacker tries to scare the victim by informing them that
their credit/debit card has been blocked. The victim becomes
worried and starts panicking. The attacker takes advantage of
this situation and asks victim to provide sensitive personal
information to re-activate the card. This information is then
misused to steal money or cause harm to the victim.
(14) Job Related Fraud
The attacker sends a fake e-mail to the victim offering a job
with an attractive salary. The victim, unfortunately, believes it
and follows the instructions. The attacker then steals the money
or harms the victim physically.
ONLINE BANKING FRAUDS
What are Online Banking Frauds?
Nowadays, all banking services are shifting online. Services
like retrieving account statement, funds transfer to other
accounts, requesting a cheque book, preparing demand draft
etc. can all be done online. Most of these services can be done
sitting at home without physically visiting the bank. As the
services are shifting towards online platforms, cyber frauds
related to banking are also increasing. Just like we protect our
locker full of jewelry with a lock and key, we must protect our
online bank accounts with strong passwords. If the key is
stolen, then the jewelry will be stolen. Similarly, if the
password is stolen, then the money in the bank accounts will be
stolen. Hence, protection of bank accounts with strong
passwords becomes highly essential. Let us look at some
examples of online banking fraud.
Digital Payments Applications related attacks
Digital payments have become very common in today‟s life.
However, they do pose a threat if the account is hacked.
Hacking of Bank Account due to Weak Password
In this type of attack, the attacker hacks into the victim‟s
account by using a program to guess commonly used
passwords. Once the account is hacked, the attacker can steal
money or perform an illegal transaction in order to defame or
frame the victim.
Hacking of Multiple Accounts due to same password
If same password is used for multiple accounts, then hacking of
one account may also lead to hacking of other accounts.
CONCLUSION
The model presented in this project demonstrates that Support
Vector Machine (SVM) is an elegant and robust method for
binary classification in a large dataset. Regardless of the
nonlinearity of the decision boundary, SVM is able to classify
between fake and genuine profiles with a reasonable degree of
accuracy (>90%). This method can be extended on any
platform that needs binary classification to be deployed on
public profiles for various purposes. This project uses only
publicly available information which makes it convenient for
organizations that want to avoid any breach of privacy, but
organizations can also use private data available to them to
further extend the capabilities of the proposed model.

REFERENCES

a) J. H. Parmelee and S. L. Bichard, Politics and the twitter

revolution: How tweets influence the relationship between
political leaders and the public, Lexington books, 2011.
b) L. Bilge, T. Strufe, D. Balzarotti, and E. Kirda, “All your
contacts are belong to us: automated identity theft attacks
on social networks,” in Proceedings of the 18th
international conference on World wide web, pp. 551–
560, Madrid, Spain, 2009. View at: Publisher Site | Google
Scholar