Leveraging Analysis of User Behavior to Identify Malicious Activities in Large-Scale Social Networks
- 18 September 2017
- journal article
- research article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Industrial Informatics
- Vol. 14 (2) , 799-813
Abstract
With the enormous growth and volume of online social networks and their features, along with the vast number of socially connected users, it has become difficult to explain the true semantic value of published content for the detection of user behaviors. Without understanding the contextual background, it is impractical to differentiate among various groups in terms of their relevance and mutual relations, or to identify the most significant representatives from the community at large. In this paper, we propose an integrated social media content analysis platform that leverages three levels of features, i.e., user-generated content, social graph connections, and user profile activities, to analyze and detect anomalous behaviors that deviate significantly from the norm in large-scale social networks. Several types of analyses have been conducted for a better understanding of the different user behaviors in the detection of highly adaptive malicious users. We attempted a novel approach regarding the process of data extraction and classification to contextualize large-scale networks in a proper manner. We also collected a significant number of user profiles from Twitter and YouTube, along with around 13 million channel activities. Extensive evaluations were conducted on real-world datasets of user activities for both social networks. The evaluation results show the effectiveness and utility of the proposed approach.Keywords
Funding Information
- Deanship of Scientific Research at King Saud University, Riyadh, Saudi Arabia (RG-228)
This publication has 42 references indexed in Scilit:
- Profiling Online Social Behaviors for Compromised Account DetectionIEEE Transactions on Information Forensics and Security, 2016
- Comparing Twitter and Facebook user behavior: Privacy and other aspectsComputers in Human Behavior, 2015
- VoteTrust: Leveraging Friend Invitation Graph to Defend against Social Network SybilsIEEE Transactions on Dependable and Secure Computing, 2015
- Analysis and Detection of Fake Views in Online Video ServicesACM Transactions on Multimedia Computing, Communications, and Applications, 2015
- Communities, Random Walks, and Social Sybil DefenseInternet Mathematics, 2014
- Online Social Networks: Threats and SolutionsIEEE Communications Surveys & Tutorials, 2014
- SybilBelief: A Semi-Supervised Learning Approach for Structure-Based Sybil DetectionIEEE Transactions on Information Forensics and Security, 2014
- Leveraging Social Feedback to Verify Online Identity ClaimsACM Transactions on the Web, 2014
- Uncovering social network Sybils in the wildACM Transactions on Knowledge Discovery From Data, 2014
- Understanding latent interactions in online social networksACM Transactions on the Web, 2013