TY  - CONF
ID  - www2009174
UR  - http://www2009.eprints.org/174/
A1  - Zuo, Haiqiang
A1  - Hu, Weiming
A1  - Wu, Ou
A1  - Chen, Yunfei
A1  - Luo, Guan
Y1  - 2009/04//
N2  - 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.
TI  - Detecting Image Spam Using Local Invariant Features and Pyramid Match Kernel
SP  - 1187
M2  - Madrid, Spain
AV  - public
EP  - 1187
T2  - 18th International World Wide Web Conference
ER  -