A novel email abstraction scheme for spam detection
Chi-Yao Tseng, Pin-Chieh Sung, Ming-Syan Chen⋆ · 2008
Prior studies on collaborative spam filtering with near-duplicate similarity matching scheme mainly represent each email by a succinct abstraction derived from email content text. Since these abstractions of emails cannot fully catch the evolving nature of spams, we propose in this paper a novel email abstraction scheme, which considers email layout structure to represent emails. With the proposed abstraction, we design a near-duplicate matching scheme to efficiently match each incoming email with a huge spam database.