FACT - Towards Automatic Real Time Identification of Malicious Posts on Facebook

Abstract

Online Social Networks (OSNs) witness a rise in user activity whenever a news-making event takes place. Cyber criminals exploit this spur in user-engagement levels to spread malicious content that compromises system reputation, causes financial losses and degrades user experience. In this paper to detect the malicious contents in the Facebook post using the annotation based approach and compared with the existing WebOfTrust (WOT) method. Social malware posts typically include at least one embedded URL link, since without such a link. The posts cannot lure and hurt users or propagate virally. This approach is trying to detect such posts on the walls and news feeds of Facebook users, and alert users exposed to social malware so that they do not click through on the URLs included in the posts. Final part contains the comparison between the WOT and Fact model on detecting malicious Facebook posts.This model can be used in FACT model to identify the malicious post on eltime,