FbDetector: Malicious App Tracing Using Neural Networks
Jebasty Ajitha.S 1
*,
D.Sharmila
- 1, , IN
Facebook provides developers an API that facilitates apps integration into the Facebook user experience. Recently, hackers have started taking advantage of the popularity of this third-party apps platform and deploying malicious applications. Our key contribution is in developing FbDetector (Facebook Detector) arguably the first tool focused on detecting malicious apps on Facebook. To develop FbDetector, we use information gathered by observing the posting behavior of 111K Facebook seen across 2.2 million users on Facebook. First, we identify a set of features that help us differentiate malicious apps from benign ones. In FbDetector we are using neural network classifier for training and testing benign and malicious Facebook application.
Conclusion
In this paper, using a large corpus of malicious Facebook apps observed over a 9-month period, we showed that malicious apps differ significantly from benign apps with respect to several features. For example, malicious apps are a lot of more expected to share names with other apps, and they classically request less permission than gentle apps. Leveraging our clarifications, we improved FbDetector, an truthful classifier for detecting malicious Facebook applications. Most interestingly, we highlighted the emergence of app-nets—large groups of tightly linked applications that promote each other.
We have offered the first measurement-based characterization of the popularity and usage of third-party Facebook applications. We plan to extend this work with additional datasets, improved models, and study of more dynamic aspects such as application vitality on the social graph.
References
- M. S. Rahman, T.-K.Huang, H. V. Madhyastha, and M. Faloutsos,“Efficient and scalable socware detection in online social networks,”inProc. USENIX Security, 2012, p. 32.
- H. Gao, Y. Chen, K. Lee, D. Palsetia, and A. Choudhary, “Towardsonline spam filtering in social networks,” in Proc. NDSS, 2012.
- P. Chia, Y. Yamamoto, and N. Asokan, “Is this app safe? A large scalestudy on application permissions and risk signals,” in Proc. WWW, 2012, pp. 311–320.
- “WhatApp? (beta)—A Stanford Center for Internet and SocietyWebsite with support from the Rose Foundation,”
- “MyPageKeeper,” [Online]. Available: https://www.facebook.com/apps/application.php?id=167087893342260
- C.-C. Chang and C.-J. Lin, “LIBSVM: A library for support vector machines,” Trans. Intell. Syst. Technol., vol. 2, no. 3, 2011, Art.no. 27.
- J. Ma, L. K. Saul, S. Savage, and G. M. Voelker, “Beyond blacklists:Learning to detect malicious Web sites from suspicious URLs,” inProc. KDD, 2009, pp. 1245–1254.
- A. Le, A. Markopoulou, and M. Faloutsos, “PhishDef: URL names sayit all,” in Proc. IEEE INFOCOM, 2011, pp. 191–195.Business Week. Building a Brand with Widgets.http://www.businessweek.com/technology/content/feb2008/tc20080303_000743.htm.
- “bit.ly API,” 2012 [Online]. Available: http://code.google.com/p/bitlyapi/wiki/ApiDocumentation
Keywords: Neural Networks
Citation: Jebasty Ajitha.S *, Jebasty Ajitha.S ( 2017), FbDetector: Malicious App Tracing Using Neural Networks. , 5(1): 1-5
Received: 04/06/2024; Accepted: 04/06/2024;
Published: 04/06/2024
Edited by:
Mr.ERES JOURNALSReviewed by:
Copyright: @ERES Publications.
*Correspondence: Jebasty Ajitha.S , ajitharajanjan18@gmail.com
