E-Mail Classification for Phishing Defense

摘要: We discuss a classification-based approach for filtering phishing messages in an e-mail stream. Upon arrival, various features of every are extracted. This forms the basis classification process which detects potentially harmful messages. introduce new identifying and rank established as well newly introduced according to their significance this problem. Moreover, contrast classical binary approaches (spam vs. not spam), more refined ternary data is investigated automatically distinguishes three message types: ham (solicited e-mail), spam, phishing. Experiments with representative sets illustrate that our yields better results than existing detection methods. direct proposed compared sequence two processes. Direct one-step only efficient, but also shown achieve accuracy repeated classification.