Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifier
Not on the map. Why?
Abstract (arXiv)
Minimizing an adversarial surrogate risk is a common technique for learning robust classifiers. Prior work showed that convex surrogate losses are not statistically consistent in the adversarial context -- or in other words, a minimizing sequence of the adversarial surrogate risk will not necessarily minimize the adversarial classification error. We connect the consistency of adversarial surrogate losses to properties of minimizers to the adversarial classification risk, known as adversarial Bayes classifiers. Specifically, under reasonable distributional assumptions, a convex surrogate loss is statistically consistent for adversarial learning iff the adversarial Bayes classifier satisfies a certain notion of uniqueness.
Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 24 of its 40 references that are in the map. First posted on arXiv 26 Apr 2024.
Builds on
24 of 40 references.
References · 24
- 2013Intriguing properties of neural networkscited by 5,155
- 2017Evasion Attacks against Machine Learning at Test Timecited by 689
- 2020An Analysis of Adversarial Attacks and Defenses on Autonomous Driving Modelscited by 68
- 2019Lower Bounds on Adversarial Robustness from Optimal Transportcited by 53
- 2021Calibration and Consistency of Adversarial Surrogate Lossescited by 47
- 2019Adversarial Risk via Optimal Transport and Optimal Couplingscited by 36
- 2020Calibrated Surrogate Losses for Adversarially Robust Classificationcited by 36
- 2022The Many Faces of Adversarial Riskcited by 28
- 2021A Finer Calibration Analysis for Adversarial Robustnesscited by 26
- 2021On the Existence of the Adversarial Bayes Classifier (Extended Version)cited by 25
- 2018Generalizability vs. Robustness: Adversarial Examples for Medical Imagingcited by 23
- 2022The Multimarginal Optimal Transport Formulation of Adversarial Multiclass Classificationcited by 21
12 more
- 2021The Geometry of Adversarial Training in Binary Classificationcited by 20
- 2020Adversarial Classification: Necessary conditions and geometric flowscited by 19
- 2022Existence and Minimax Theorems for Adversarial Surrogate Risks in Binary Classificationcited by 15
- 2023Adversarial Training Should Be Cast as a Non-Zero-Sum Gamecited by 13
- 2022Towards Consistency in Adversarial Classificationcited by 12
- 2023On the existence of solutions to adversarial training in multiclass classificationcited by 9
- 2020ATRO: Adversarial Training with a Rejection Optioncited by 8
- 2023The Adversarial Consistency of Surrogate Risks for Binary Classificationcited by 6
- 2023On the Role of Randomization in Adversarially Robust Classificationcited by 4
- 2023Stratified Adversarial Robustness with Rejectioncited by 4
- 2024A Notion of Uniqueness for the Adversarial Bayes Classifiercited by 3
- 2023On Achieving Optimal Adversarial Test Errorcited by 1
Built on by
Citing papers per year: 2025: 2.
2 papers.