An artificial immunity-based spam detection system

The performance evaluation against a standard spam collection and reference systems shows that the proposed spam detection system performs well compared to other systems with large sets of features, rules, or external evidences.

Abstract

Spam is considered a significant security problem for computer users everywhere. Spammers exploit a variety of tricks to conceal parts of messages that can be used to identify spam. A number of different spam detection techniques have been proposed using a large number of message features, heuristic rules, or evidences from other detectors. This paper presents an email feature extraction technique for spam detection based on artificial immune systems. The proposed method extracts a set of four features that can be used as inputs to a spam detection model. The performance evaluation against a standard spam collection and reference systems shows that the proposed spam detection system performs well compared to other systems with large sets of features, rules, or external evidences. The detection performance of the best system in this study is 0.91% and 1.95% of false positive and false negative rates, respectively.