Timezone: »

Mixed Nash Equilibria in the Adversarial Examples Game
Laurent Meunier · Meyer Scetbon · Rafael Pinot · Jamal Atif · Yann Chevaleyre

Thu Jul 22 09:00 AM -- 11:00 AM (PDT) @

This paper tackles the problem of adversarial examples from a game theoretic point of view. We study the open question of the existence of mixed Nash equilibria in the zero-sum game formed by the attacker and the classifier. While previous works usually allow only one player to use randomized strategies, we show the necessity of considering randomization for both the classifier and the attacker. We demonstrate that this game has no duality gap, meaning that it always admits approximate Nash equilibria. We also provide the first optimization algorithms to learn a mixture of classifiers that approximately realizes the value of this game, \emph{i.e.} procedures to build an optimally robust randomized classifier.

Author Information

Laurent Meunier (Facebook/Dauphine)
Meyer Scetbon (CREST, ENSAE)
Rafael Pinot (EPFL)
Jamal Atif (Université Paris-Dauphine)
Yann Chevaleyre (Univ. Paris Dauphine)

Related Events (a corresponding poster, oral, or spotlight)

More from the Same Authors