Feature set identification for detecting suspicious URLs using Bayesian classification in social networks

Social network services (SNSs) are increasing popular. Communicating with friends forms a social network that can be used to promptly share information with friends. In targeted attacks, SNSs are often used to collect personal information and craft attacks based on a specific user profile. Malware can be used to facilitate social relationship, sends messages containing malicious URLs, lures users to click on these URLs by employing social engineering techniques; then replicates through the social network over and over again. Because users are curious and trust in their friends, they typically click on malicious URLs without verification. In this study, a feature set is presented that combines the features of traditional heuristics and social networking. Furthermore, a suspicious URL identification system for use in social network environments is proposed based on Bayesian classification. The experimental results indicate that the proposed approach achieves a high detection rate.