Poster
Nonzero-sum Adversarial Hypothesis Testing Games
Sarath Yasodharan · Patrick Loiseau
East Exhibition Hall B + C #224
Keywords: [ Game Theory and Computational E ] [ Algorithms -> Adversarial Learning; Applications -> Privacy, Anonymity, and Security; Theory ] [ Theory ] [ Large Deviations and Asymptotic Analysis ]
We study nonzero-sum hypothesis testing games that arise in the context of adversarial classification, in both the Bayesian as well as the Neyman-Pearson frameworks. We first show that these games admit mixed strategy Nash equilibria, and then we examine some interesting concentration phenomena of these equilibria. Our main results are on the exponential rates of convergence of classification errors at equilibrium, which are analogous to the well-known Chernoff-Stein lemma and Chernoff information that describe the error exponents in the classical binary hypothesis testing problem, but with parameters derived from the adversarial model. The results are validated through numerical experiments.
Live content is unavailable. Log in and register to view live content