Protecting classifiers from attacks

DOI10.1214/24-STS922MaRDI QIDQ6579153zbMATH OpenFDO

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

Publication date 25 July 2024

Published in Statistical Science (Search for Journal in Brave)

zbMATH Keywords

classificationBayesian methodsadversarial risk analysisadversarial machine learningdeep models

Mathematics Subject Classification ID

Statistics (62-XX)

Cites work

• scientific article; zbMATH DE number 3954047 (Why is no real title available?)
• scientific article; zbMATH DE number 47310 (Why is no real title available?)
• A Stochastic Approximation Method
• Adversarial classification: an adversarial risk analysis approach
• Adversarial machine learning
• Adversarial risk analysis
• Adversarial risk analysis: the Somali pirates case
• Approximating Bayes in the 21st century
• Augmented probability simulation methods for sequential games
• Constructing summary statistics for approximate Bayesian computation: semi-automatic approximate Bayesian computation. With discussion and authors' reply
• Deep learning
• Estimating classification error rate: repeated cross-validation, repeated hold-out and bootstrap
• Expert judgement in risk and decision analysis
• Generalized accept-reject sampling schemes
• Inference for Stereological Extremes
• Large-scale machine learning with stochastic gradient descent
• On players' models of other players: Theory and experimental evidence
• Pattern recognition and machine learning.
• Random forests
• Robust Bayesian analysis
• Robust Bayesian inference via coarsening
• Some statistical challenges in automated driving systems
• The Elements of Statistical Learning

Cited in

(1)

• On global robustness of an adversarial risk analysis solution

This page was built for publication: Protecting classifiers from attacks

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6579153)