Adversarial classification: An adversarial risk analysis approach

Abstract

Classification problems in security settings are usually contemplated as confrontations in which one or more adversaries try to fool a classifier to obtain a benefit. Most approaches to such adversarial classification problems have focused on game theoretical ideas with strong underlying common knowledge assumptions, which are actually not realistic in security domains. We provide an alternative framework to such problem based on adversarial risk analysis, which we illustrate with several examples. Computational and implementation issues are discussed.

Published in the International Journal for Approximate Reasoning

References in corpus (4)

• Explaining and Harnessing Adversarial Examples
• Wild Patterns: Ten Years After the Rise of Adversarial Machine Learning
• Poisoning Attacks against Support Vector Machines
• Security Evaluation of Pattern Classifiers under Attack

Cited by in corpus (9)

• Adversarial Machine Learning: Bayesian Perspectives
• Opponent Aware Reinforcement Learning
• Manipulating hidden-Markov-model inferences by corrupting batch data
• Protecting Classifiers From Attacks
• Adversarial attacks against Bayesian forecasting dynamic models
• Improve Adversarial Robustness via Weight Penalization on Classification Layer
• A Statistician Teaches Deep Learning
• Contributions to Large Scale Bayesian Inference and Adversarial Machine Learning
• Gradient Methods for Solving Stackelberg Games