期刊
IEEE TRANSACTIONS ON INFORMATION FORENSICS AND SECURITY
卷 18, 期 -, 页码 831-845出版社
IEEE-INST ELECTRICAL ELECTRONICS ENGINEERS INC
DOI: 10.1109/TIFS.2022.3231095
关键词
Testing; Games; Nash equilibrium; Training; Perturbation methods; Markov processes; Machine learning algorithms; Game theory; M-ary sequential hypothesis testing; adversary
In this paper, a novel M-ary sequential hypothesis testing problem is formulated as a sequential adversarial hypothesis testing game, played between a decision maker and an adversary. The decision maker aims to minimize the expectation of the stopping time, while the adversary aims to maximize it. Strategies are derived to attain the asymptotic Nash equilibrium of the game. Numerical results validate the theoretical findings.
In this paper, we consider a novel M-ary sequential hypothesis testing problem in which an adversary is present and perturbs the distributions of the samples before the decision maker observes them. This problem is formulated as a sequential adversarial hypothesis testing game played between the decision maker and the adversary. This game is a zero-sum and strategic one. We assume the adversary is active under all hypotheses and knows the underlying distribution of observed samples. We adopt this framework as it is the worst-case scenario from the perspective of the decision maker. The goal of the decision maker is to minimize the expectation of the stopping time to ensure that the test is as efficient as possible; the adversary's goal is, instead, to maximize the stopping time. We derive a pair of strategies under which the asymptotic Nash equilibrium of the game is attained. We also consider the case in which the adversary is not aware of the underlying hypothesis and hence is constrained to apply the same strategy regardless of which hypothesis is in effect. Numerical results corroborate our theoretical findings.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据