Spam Detection by Game theory

There are number of datamining applications that are fighting with Adversaries, Spam filtering to intrusion detection is as an example. For reducing the classifier accuracy, Adversary intentionally manipulate data. Consequently, in all these applications initially successful classifiers will decline easily. In this paper, we model the interaction between the classifier and the adversary as a two players sequential game then we model the interaction as an optimization problem and solve it using evolutionary strategy. Finally, simulation results show the good performance of the proposed algorithm, and improves accuracy spam detection on several real world data sets.