研究著作內容
A Robust Local Feature-based Scheme for Phishing Page Detection and Discrimination
(NOTE: Sheng-Wei Chen is also known as Kuan-Ta Chen.)

Abstract
Phishing, which tries to trick Internet users into revealing their confidential information, such as their bank accounts and credit card numbers, is a form of online identity theft associated with both social engineering and technical subterfuge. According to a survey by Gartner, Inc., in 2007, more than $3.2 billion was lost due to phishing attacks in the US and 3.6 million adults lost money in such attacks.

In this paper, we present an effective image-based phishing detection scheme with local content features. We collected 2058 phishing webpages on 74 target sites, and used an invariant local descriptor, the Contrast Context Histogram (CCH) descriptor, to compute the similarity degree between the suspected pages and the official pages. Large-scale experiments involving more than 44000 page-by-page examinations were carried out. The results indicated that the proposed scheme can achieve a successful recognition rate as high as 96% with a computation time cost of less than 0.2 seconds per phishing identification.

A revised version of this paper: Fighting Phishing with Discriminative Keypoint Features of Webpages


Citation
Jau-Yuan Chen and Kuan-Ta Chen, "A Robust Local Feature-based Scheme for Phishing Page Detection and Discrimination," In Proceedings of Web 2.0 Trust Workshop in conjunction with IFIPTM 2008, 2008.

BibTex
@INPROCEEDINGS{chen08:phishing,
  TITLE      = {A Robust Local Feature-based Scheme for Phishing Page Detection and Discrimination},
  AUTHOR     = {Jau-Yuan Chen and Kuan-Ta Chen},
  BOOKTITLE  = {Proceedings of Web 2.0 Trust Workshop in conjunction with IFIPTM 2008},
  YEAR       = {2008}
}