Adversarial classification: an adversarial risk analysis approach

DOI10.1016/J.IJAR.2019.07.003zbMATH Open1468.68046arXiv1802.07513OpenAlexW2788527767WikidataQ127462288 ScholiaQ127462288MaRDI QIDQ2302772FDOQ2302772

Alberto Redondo, Fabrizio Ruggeri, Roi Naveiro, David Ríos Insua

Publication date: 26 February 2020

Published in: International Journal of Approximate Reasoning (Search for Journal in Brave)

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.

Full work available at URL: https://arxiv.org/abs/1802.07513

Recommendations

• Adversarial classification using signaling games with an application to phishing detection
• Machine learning in adversarial environments
• Scalable Optimal Classifiers for Adversarial Settings Under Uncertainty
• Classifier evaluation and attribute selection against active adversaries
• Adversarial risk analysis

zbMATH Keywords

classificationBayesian methodsrobustnessinfluence diagramsadversarial machine learning

Mathematics Subject Classification ID

Classification and discrimination; cluster analysis (statistical aspects) (62H30) Learning and adaptive systems in artificial intelligence (68T05) Computer security (68M25)

Cites Work

• Title not available (Why is that?)
• Bayesian Classification of Tumours by Using Gene Expression Data
• Multi-agent influence diagrams for representing and solving games.
• Safe and Effective Importance Sampling
• Adversarial Risk Analysis
• Network games: theory, models, and dynamics
• Classifier evaluation and attribute selection against active adversaries
• Title not available (Why is that?)
• Estimating classification error rate: repeated cross-validation, repeated hold-out and bootstrap
• Decision Analysis by Augmented Probability Simulation
• Information enhancement -- a tool for approximate representation of optimal strategies from influence diagrams
• Regression Metamodels for Simulation with Common Random Numbers: Comparison of Validation Tests and Confidence Intervals
• Computer Age Statistical Inference
• Title not available (Why is that?)

Cited In (16)

• Adversarial risk analysis: an overview
• Adversarial Risk Analysis for Auctions Using Mirror Equilibrium and Bayes Nash Equilibrium
• Gradient methods for solving Stackelberg games
• When Should You Defend Your Classifier?
• Protecting classifiers from attacks
• Health care fraud classifiers in practice
• Editorial. Special issue on robustness in probabilistic graphical models
• Decision support issues in automated driving systems
• A statistician teaches deep learning
• An Adversarial Risk Analysis Framework for Batch Acceptance Problems
• Analysis of classifiers' robustness to adversarial perturbations
• Adversarial risk analysis for first‐price sealed‐bid auctions
• Adversarial Machine Learning: Bayesian Perspectives
• On global robustness of an adversarial risk analysis solution
• Scalable Optimal Classifiers for Adversarial Settings Under Uncertainty
• Manipulating hidden-Markov-model inferences by corrupting batch data

Uses Software

• UCI-ml
• PRMLT

This page was built for publication: Adversarial classification: an adversarial risk analysis approach

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2302772)