International Journal for Development of Computer Science & Technology (IJDCST)
SMTP servers equipped with machine learning algorithms such as Naive Bayes, SVM models are claimed effective in handling spam e-mails, but the results appear to be farfetched considering spam emails finding their way into the authors' inbox once in a while. So far the spammers appear to circumvent many barriers set up by spam detection system. But the vulnerability of the spammers is their message. So content-based filters are the way to stop email spam. Recently the notion of collaborative spam filtering with near-duplicate similarity matching scheme has been widely discussed and implemented.