A semi-supervised learning approach for detection ofphishing webpages

摘要

This paper proposes a new phishing webpage detection approach based on a kind of semi-supervisedlearning method-transductive support vector machine (TSVM). Firstly the features of web image areextracted for complementing the disadvantage of phishing detection only based on document objectmodel (DOM); they include gray histogram, color histogram, and spatial relationship between subgraphs.Then the features of sensitive information are examined by using page analysis based on DOM objects.In contrast to the drawback of support vector machine (SVM) algorithm which simply trains classifierby learning little and poor representative labeled samples, this method introduces the TSVM to trainclassifier that it takes into account the distribution information implicitly embodied in the large quantityof the unlabeled samples, and have better performance than SVM. The experimental results show thatthe proposed method not only achieves better classification accuracy, but also has strong applicability asthe independent method of phishing detection.