Detecting image spam using local invariant features and pyramid match kernel

Haiqiang Zuo, Weiming Hu, Ou Wu, Yunfei Chen, Guan Luo

Abstract: 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.