Detecting Malicious Facebook Applications Using Classification Technique

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 – 0882
185
Volume 6, Issue 3, March 2017
Detecting Malicious Facebook Applications Using Classification Technique
Shivani Sundaram, Shruti V. Mhatre, Prof. Shilpa Satre

Bharati Vidyapeeth College of Engineering.
Sector-7, C.B.D, Belpada, Navi Mumbai-400614, India
Abstract 1) These applications can reach large numbers of users

Online social media services like Facebook witness and from them to their friends and so on to spread spam.
antremendous increase in user activity when an event 2) These applications can obtain users’ personal
takes place in the real world. Users also upload their information such as email address, birth date and many
personal information and photos to these sites without other sensitive Information
knowing much about the privacy of the site. With more 3) These applications can “re-produce" themselves by
than a thousand applicationsinstalls a day, third-party making other malicious applications popular. In other
applications are a major reason for the popularity and words, there is motive and opportunity, which results in
addictiveness of Facebook. Unfortunately, hackers many malicious applications spreading on Facebook
knows the potential of using applications for spreading every day.
malware and spam to get private or sensitive Despite of these many risks which users are exposed to,
information and unauthorized access of the user’s users have very few or little information about these
account. The researchers are working in this areas threats.
andso far, the research community has focused on
detecting malicious posts and campaigns. In this II. EXISTING METHOD
proposed system we are developing an application
which focused on detecting malicious applications on 1) Detecting and Characterizing Social Spam
Facebook. To develop system, we use information Campaigns
gathered by observing the posting behavior of Authors: Hongyu Gao, Jun Hu, Christo Wilson, Zhichun
Facebook applications seen across users on Facebook. Li, Yan Chen, Ben Y. Zhao.
First, we identify a set of features that help us Description: Authors presented a primary study to
distinguish malicious applications from real ones. This calculate and analyze spam campaigns launched on
will help in reducing malicious attack. The aim of the online social networks. They calculated a huge
project is to observe at what extent can we train the anonymized dataset of asynchronous “wall” messages in
system to correctly identify the malicious applications between Facebook users.
in Facebook to achieve ultimate objective to reduce the System detected generally 200,000 malicious wall posts
malicious attack. with embedded URLs, originating from more than
57,000 user accounts. Authors found that more than 70%
Keywords: Online social media, facebook, of all malicious wall posts advertise phishing sites. To
malicious, attacks, hackers. study the distinctiveness of malicious accounts, and see
that more than 97% are compromised accounts, rather
than “fake “accounts formed solely for the principle of
I. INTRODUCTION spamming. Finally, when adjusted to the local time of the
sender, spamming dominates actual wall post in the early
The social networking sites like facebook enables third morning hours when users are normally asleep.
party applications to Boost up the user experience on
these platforms. Such enhancements include interesting 2) Social Applications: Exploring A More Secure
or entertaining ways of communicating among online Framework
friends, and diverse activities such as playing a lots of Authors: Andrew Besmer, Heather Richter Lipford,
exciting games or chaating with friends. Recently, Mohamed Shehab, Gorrell Cheek
hackers have started taking advantage of the popularity Description: OSNs such as Orkut, Facebook and others
of this third-party apps platform and deploying malicious have grown-up rapidly, with hundreds to millions of
applications. Malicious applications can provide a active users. A new feature provided on several sites is
lucrative business for hackers, given the popularity of social applications and services written by third party
OSNs, with Facebook leading the way with millions of developers that supply additional functionality linked to
active users There are many ways that hackers can a user’s profile. However, Presentapplication platforms
beneﬁt from a malicious applications: put users at risk by permitting the discovery of huge
www.ijsret.org
186
amounts of personal data and information to these The architecture diagram will show the functioning of
applications and theirdevelopers. This paper generally our system. Whenever an application is popped out in
abstracts main view and defines the current access front of user and if user wants to visit it then, the user
control model gave to theseapplications, and builds on it will request the facebook server for access. The facebook
to generate a more secure framework. server will pass request to application server after which
the request will be received by our proposed system. Our
III. PROPOSED SYSTEM system will look for it in our database that whether the
URL from which the application has come is in active or
In this work, we are going to build a system, which use blocked state, accordingly it will decide whether to grant
classification technique to detect whether an applications the permission to user or not.
is malicious or not. For this, the system will use data
stored in our database. Advantages
For this, our work will contribute the following: 1) The proposed system is a tool to detect a
 First, we have designed a social networking Malicious application.
site(like facebook). 2) It will provide security to the user’s account
 In that we can do all basic task like login, form hackers.
signup, make friend, like, comment, make post,
etc.
IV. CONCLUSION
 All the data related to all activities on the site is
stored in the database.
 In our work if any application comes from the Till now, the researchers have found techniques to detect
third party then first the system will check if that malicious posts and spams. But, due to these third party
URL is present in active or block state in our applications being hosted on facebook has put millions
database. of users at security risk. Hence, in this work, we have
 If active, then the system will allow it to post proposed a system which will use classification
application. techniques to detect whether an application is malicious
or not.This work is a small contribution in this area for
 If blocked, then the system will not allow it to providing security to the users and reducing the
post application. malicious activity.
If any application comes from a URL which is not in our
database, that is for the first time that URL is hosting any Hope, this small contribution will help in further
application than the system will allow it to host. research related to this area and improve the security
In this way, we can suggest a way to secure user over time.
accounts from hackers.
Proposed System Architecture Diagram REFERENCES
[1] “Wiki: Facebook platform,” 2014 [Online].

Available:http://en.wikipedia.org/wiki/Facebook_Platfor
m.
[2] H. Gao et al. “Detecting and characterizing social

spam campaigns,” in Proc. IMC, 2010, pp. 35–47.
[3] H. Gao, Y. Chen, K. Lee, D. Palsetia, and A.

Choudhary, “Towards online spam filtering in social
networks,” in Proc. NDSS, 2012.
[4] A. Besmer, H. R. Lipford, M. Shehab, and G. Cheek.

Social applications: exploring a more secure framework.
In SOUPS, 2009.
Fig: Architecture Diagram
www.ijsret.org
187
[5]P. Chia, Y. Yamamoto, and N. Asokan. Is this app

safe? A large scale study on application permissions and
risk signals. In WWW, 2012.
[6]M. Gjoka, M. Sirivianos, A. Markopoulou, and X.

Yang. Poking facebook: characterization of osn
applications. In Proceedings of the first workshop on
Online social networks, WOSN, 2008.
[7] N. Wang, H. Xu, and J. Grossklags. Third-party apps

on facebook: privacy and the illusion of control. In
CHIMIT, 2011.
[8] Gaurav Parsewar, Yogesh Dalvi, Lalit Kothwade,

“Detection of Malicious Application on Online Social
Network” IJISET - International Journal of Innovative
Science, Engineering & Technology, Vol. 2 Issue 9,
September 2015.
[9] Sushma Nallamalli, Loya Chandrajit Yadav,

Karicharla Prasad, Gorla Siva Parvathi, “A Survey on
Detecting Malicious Facebook Applications using
FRApp” International Journal of Innovative Research in
Computer and Communication Engineering, Vol. 4,
Issue 2, February 2016.
www.ijsret.org

Detecting Malicious Facebook Applications Using Classification Technique

Uploaded by

Copyright:

Available Formats

Detecting Malicious Facebook Applications Using Classification Technique

Uploaded by

Document Information

Original Description:

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Detecting Malicious Facebook Applications Using Classification Technique

Uploaded by

Copyright:

Available Formats

International Journal of Scientific Research Engineering & Technology (IJSRET), ISSN 2278 – 0882

Detecting Malicious Facebook Applications Using Classification Technique

Shivani Sundaram, Shruti V. Mhatre, Prof. Shilpa Satre

Abstract 1) These applications can reach large numbers of users

[1] “Wiki: Facebook platform,” 2014 [Online].

[2] H. Gao et al. “Detecting and characterizing social

[3] H. Gao, Y. Chen, K. Lee, D. Palsetia, and A.

[4] A. Besmer, H. R. Lipford, M. Shehab, and G. Cheek.

Fig: Architecture Diagram

[5]P. Chia, Y. Yamamoto, and N. Asokan. Is this app

[6]M. Gjoka, M. Sirivianos, A. Markopoulou, and X.

[7] N. Wang, H. Xu, and J. Grossklags. Third-party apps

[8] Gaurav Parsewar, Yogesh Dalvi, Lalit Kothwade,

[9] Sushma Nallamalli, Loya Chandrajit Yadav,

You might also like