Hybrid approach for detection of malicious profiles in twitter

Abstract

Emergence of social media invokes social actors to share their information digitally. Moreover, it enables them to maintain their links with other people worldwide. Due to its massive popularity, it has become a fascinating test bed to initiate various attacks. Attackers form Sybil nodes to disseminate malicious content in order to infect legitimate users aiming to steal sensitive information, such as user's credentials. Therefore, the focus of this paper is to detect malicious profiles, specifically on the Twitter microblogging platform. We propose a hybrid approach which leverages the capabilities of machine learning techniques to identify malicious profiles. Initially, Petri net structure analyzes the user's profile and various features, and these features are then used to train classifier. This is achieved to identify malicious profiles from legitimate users. Finally, to prove the efficiency, a comparative analysis of our approach is conducted with existing state-of-the-art techniques. The experimental results reveal that our approach achieves a high detection rate of 99.16% which is better than other techniques.