Towards Online Spam Filtering in Social Networks
Download: Paper (PDF)
Date: 6 Feb 2012
Document Type: Briefing Papers
Additional Documents: Slides
Associated Event: NDSS Symposium 2012
This paper presents an online spam filtering system to inspect messages in online social networks. We propose to use text shingling and incremental clustering to reconstruct spam messages into campaigns in real-time for classification rather than examine them individually. Accordingly, the system adopts novel features that effectively characterize spam campaigns.