Adversarial classification: An adversarial risk analysis approach

2018/02/28 by Roi Naveiro, Alberto Redondo, David Rı́os Insua +2
Computer Science · Engineering · Mathematics · #Adversarial Robustness in Machine Learning #Adversarial machine learning #Adversarial system #Artificial intelligence #Bayesian Modeling and Causal Inference #Classifier (UML) #Computer science #Infrastructure Resilience and Vulnerability Analysis #Machine learning #Risk analysis (engineering) #cs.GT #cs.LG #stat.ML

paper · pdf · doi:10.1016/j.ijar.2019.07.003

published as International Journal of Approximate Reasoning, 113, 133-148 (2019) · Published in the International Journal for Approximate Reasoning

openalex publication_date 2019/07/17 · arxiv created 2019/09/24 · arxiv updated 2019/09/25 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/05

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.

Citations

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