Obtaining the threat model for e-mail phishing

Phishing is a kind of embezzlement that uses social engineering in order to obtain personal information from its victims, aiming to cause losses. In the technical literature only the hit rate of the classifiers is mentioned to justify the effectiveness of the phishing detecting techniques. Aspects such as the accuracy of the classifier results (false positive rate), computational effort and the number of features used for phishing detection are rarely taken into account. In this work we propose a technique that yields the minimum set of relevant features providing reliability, good performance and flexibility to the phishing detection engine. The experimental results reported in this work show that the proposed technique could be used to optimize the detection engine of the anti-phishing scheme.