Research on Behavior Statistic Based Spam Filter

The spread of spam made a lot of interference to Internet users, and wasted network bandwidth. Anti-spam technology has been developed to the third-generation technology, behavior recognition technology. Many studies have focused on the detection of abnormal behavior in the period of SMTP conversation. In this paper, userpsilas typical sending behavior mathematical model is concerned. To find the abnormal behavior different from the typical behavior, similarity is computed between behaviors of separate users, or between the same userpsilas behavior in long-time and short-time. Combing the common features of email messages, especially most of spam presence of hyperlink, the URL model is also built. Lastly, by Naive Bayes model, several behavior recognizing models can cooperate to detect spam.