论文信息 - Web phishing detection using classifier ensemble

Web phishing detection using classifier ensemble

This research adapts and develops various methods in Artificial Intelligent (A.I) field to improve web phishing detection. Based on the features from Carnegie Mellon Anti-phishing and Network Analysis Tool (CANTINA), we add, modify or reduce features in case of using to train a machine learning method. We also add our developed features called homepage similarity features to the machine. Moreover, we applied the classifier ensemble concept to the study. After training with 500 phishing web pages and 500 non-phishing web pages, the experiments on 1,500 pages per each class showed that our proposed methodology could boost accuracy up to approximately 30% from traditional heuristic method's results.

Arnon Rungsawang | Nuttapong Sanglerdsinlapachai

[1] Jason I. Hong,et al. A hybrid phish detection approach by identity discovery and keywords retrieval , 2009, WWW '09.

[2] D. Ruta,et al. An Overview of Classifier Fusion Methods , 2000 .

[3] Daisuke Miyamoto,et al. An Evaluation of Machine Learning-Based Methods for Detection of Phishing Sites , 2008, ICONIP.

[4] Lorrie Faith Cranor,et al. Cantina: a content-based approach to detecting phishing web sites , 2007, WWW '07.

[5] Xuhua Ding,et al. Anomaly Based Web Phishing Page Detection , 2006, 2006 22nd Annual Computer Security Applications Conference (ACSAC'06).

[6] Eric Medvet,et al. Visual-similarity-based phishing detection , 2008, SecureComm.

[7] Michael S. Hsiao,et al. Evaluation of Online Resources in Assisting Phishing Detection , 2009, 2009 Ninth Annual International Symposium on Applications and the Internet.

[8] Lorrie Faith Cranor,et al. Phinding Phish: An Evaluation of Anti-Phishing Toolbars , 2007, NDSS.

[9] Ian Witten,et al. Data Mining , 2000 .

[10] Xiaotie Deng,et al. Detecting Phishing Web Pages with Visual Similarity Assessment Based on Earth Mover's Distance (EMD) , 2006, IEEE Transactions on Dependable and Secure Computing.