%0 Conference Paper
%A Zuo, Haiqiang
%A Hu, Weiming
%A Wu, Ou
%A Chen, Yunfei
%A Luo, Guan
%B 18th International World Wide Web Conference
%C Madrid, Spain
%D 2009
%F www2009:174
%P 1187-1187
%T Detecting Image Spam Using Local Invariant Features and Pyramid Match Kernel
%U http://www2009.eprints.org/174/
%X 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.