compromised Account Detection using Friends Collusiveness in Online Social Networks
Vaslit.J1
*,
S. Arulkumar
- 1Anna University Chennai, PG student, Lord Jegannath College of Engineering & Technology, Nagercoil, Tamilnadu, IN
Compromised accounts in Online Social Networks (OSNs) are more positive than Sybil accounts to spammers and other malicious OSN attacker. Malicious parties exploit the well-established relations and trust connection between the genuine account owners and their friends. In this paper we study the friend’s collusiveness feature of OSN users, i.e. their usage of OSN services, and the application of which in detecting compromised accounts. We propose a set of social friends’ collusiveness features that can effectively characterize the user social activities on OSNs. We validate the efficacy of these friends’ collusiveness features by collecting and analyzing real user click streams to an OSN website. Based on our measurement study, we devise individual user’s social behavioral profile by combining its respective friend’s collusiveness features metrics. A social behavioral profile correctly reflects a user’s OSN activity patterns. While an authentic owner conforms to its account’s social behavioral profile reluctantly, it is hard and costly for imposters to feign.
Conclusion
Our evaluation on sample Facebook users indicate that we can achieve high detection accuracy when behavioral profiles are built in a complete and accurate fashion. We presented a novel approach to detect compromised accounts in social networks. More precisely, we developed statistical models to characterize the behavior of social network users, and in the future we used anomaly detection techniques to identify sudden changes in their behavior.
Author Contributions
hs;q3)JCiIIY
Conflict of Interest Statement
hs;q3)JCiIIY
References
- H. Gao, J. Hu, C. Wilson, Z. Li, Y. Chen, and B. Y. Zhao. Detecting and characterizing social spam campaigns. In Proceedings of the 10th ACM SIGCOMM conference on Internet measurement, IMC ’10, pages 35–47, Melbourne, Australia, 2010. ACM
- K.-I. Goh and A.-L. Barab´asi. Burstiness and memory in complex systems. EPL (Europhysics Letters), 81(4):48002, 2008.
- 250,000 twitter accounts hacked. http://www.cnn.com/2013/02/01/tech/social-media/twitter-hacked.
- 50,000 facebook accounts hacked. http://www.ktsm.com/news/ thousands-of-facebook-accounts-hacked.
- Detecting suspicious account activity. http://googleonlinesecurity.blogspot.com/2010/03/detecting-suspicious-account-activity.html.
- Facebook tracks the location of logins for better security. http:// www.zdnet.com/blog/weblife/facebook-adds-better-security- tracks- the location- of-your-logins/2010.
- H. Gao, Y. Chen, and K. Lee. Towards online spam filtering in social networks. In Symposium on NetowrkandDistributed System Security, NDSS 12’, San Diego, CA USA. Internet Society.
- C. Yang, R. C. Harkreader, and G. Gu. Die free or live hard? Empirical evaluation and new design for fighting evolving twitter spammers. In Proceedings of the 14th international conference on Recent Advances in Intrusion Detection, RAID’11, pages 318–337, Menlo Park, CA, 2011. Springer-Verlag.
- M. Egele, G. Stringhini, C. Kruegel, and G. Vigna. Compa: Detecting compromised accounts on social networks. In Symposium on Network andDistributed System Security, NDSS 13’, San Diego, CA USA. Internet Society.
- K. Thomas, D. McCoy, C. Grier, A. Kolcz, and V. Paxon. Trafcking fraudulent accounts: The role of the underground market in twitter spam and abuse. In Proceddings of 22nd USENIX Security Symposium, USENIX Security 13’, Washington D.C., USA, 2013.
Keywords: Online Social Networks (OSNs)
Citation: Vaslit.J*, Vaslit.J ( 2017), compromised Account Detection using Friends Collusiveness in Online Social Networks . , 5(1): 1-8
Received: 03/06/2024; Accepted: 04/06/2024;
Published: 04/06/2024
Edited by:
Mr.ERES JOURNALS