A game-theoretic approach to adversarial linear Gaussian classification. (September 2021)

• Record Type: Journal Article
• Authors: Farokhi, Farhad
• Is Part Of: IFAC journal of systems and control. Volume 17(2021)
• Publication Date: 2021-09
• Subjects: Binary classification -- Linear support vector machine -- Gaussian -- Adversarial machine learning -- Game theory; Automatic control -- Periodicals; Relay control systems -- Periodicals; Embedded computer systems -- Periodicals; Feedback control systems -- Periodicals; Artificial intelligence -- Periodicals; Artificial intelligence; Automatic control; Embedded computer systems; Feedback control systems; Relay control systems; Electronic journals; Periodicals; 629.89
• DOI: 10.1016/j.ifacsc.2021.100163
• Languages: English
• ISSNs: 2468-6018

Abstract

Abstract: We employ a game-theoretic model to analyse the interaction between an adversary and a classifier. There are two (i.e., positive and negative) classes to which data points can belong. The adversary wants to maximize the probability of miss-detection for the positive class (i.e., false negative probability) while it does not want to significantly modify the data point so that it still maintains favourable traits of the original class. The classifier, on the other hand, wants maximize the probability of correct detection for the positive class (i.e., true positive probability) subject to a lower-bound on the probability of correct detection for the negative class (i.e., true negative probability). For conditionally Gaussian data points (conditioned on the class) and linear support vector machine classifiers, we rewrite the optimization problems of the adversary and the classifier as convex problems and use best response dynamics to learn an equilibrium of the game. This results in computing a linear support vector machine classifier that is robust against adversarial input manipulations.