174 4 archive disk0/00/00/01/74 2009-04-06 19:14:00 2009-04-07 14:03:08 2009-04-06 19:14:00 conference_item show 0 Zuo Haiqiang Chinese Academy of Sciences Hu Weiming Chinese Academy of Sciences Wu Ou Chinese Academy of Sciences Chen Yunfei Chinese Academy of Sciences Luo Guan Chinese Academy of Sciences Poster Session Detecting Image Spam Using Local Invariant Features and Pyramid Match Kernel pub public poster Image spam is a new obfuscating method which spammers invented to more effectively bypass conventional text based spam filters. In this paper, we extract local invariant features of images and run a one-class SVM classifier which uses the pyramid match kernel as the kernel function to detect image spam. Experimental results demonstrate that our algorithm is effective for fighting image spam. 2009-04 1187-1187 18th International World Wide Web Conference Madrid, Spain April 20th-24th, 2009 conference TRUE 174 4 174 1 application/pdf en public
p1187.pdf
published p1187.pdf 670697 http://www2009.eprints.org/174/1/p1187.pdf