mlsanityData to 14 Oct 2026

Towards Calibrated Losses for Adversarial Robust Reject Option Classification

arXiv 2410.10736 ↗First posted 14 Oct 2024cs.LG stat.MLcited by 0

Not on the map. Why?

Abstract (arXiv)

Robustness towards adversarial attacks is a vital property for classifiers in several applications such as autonomous driving, medical diagnosis, etc. Also, in such scenarios, where the cost of misclassification is very high, knowing when to abstain from prediction becomes crucial. A natural question is which surrogates can be used to ensure learning in scenarios where the input points are adversarially perturbed and the classifier can abstain from prediction? This paper aims to characterize and design surrogates calibrated in "Adversarial Robust Reject Option" setting. First, we propose an adversarial robust reject option loss ℓdγ and analyze it for the hypothesis set of linear classifiers (H_textrmlin). Next, we provide a complete characterization result for any surrogate to be (ℓdγ,H_textrmlin)- calibrated. To demonstrate the difficulty in designing surrogates to ℓdγ, we show negative calibration results for convex surrogates and quasi-concave conditional risk cases (these gave positive calibration in adversarial setting without reject option). We also empirically argue that Shifted Double Ramp Loss (DRL) and Shifted Double Sigmoid Loss (DSL) satisfy the calibration conditions. Finally, we demonstrate the robustness of shifted DRL and shifted DSL against adversarial perturbations on a synthetically generated dataset.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 18 of its 27 references that are in the map. First posted on arXiv 14 Oct 2024.

Builds on

18 of 27 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  3. 2013Intriguing properties of neural networkscited by 5,155
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,340
  6. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 567
  7. 2018Certified Defenses against Adversarial Examplescited by 306
  8. 2018Deep k-Nearest Neighbors: Towards Confident, Interpretable and Robust Deep Learningcited by 207
  9. 2022Rethinking Lipschitz Neural Networks and Certified Robustness: A Boolean Function Perspectivecited by 51
  10. 2019ML-LOO: Detecting Adversarial Examples with Feature Attributioncited by 48
  11. 2021Calibration and Consistency of Adversarial Surrogate Lossescited by 47
  12. 2019On the Calibration of Multiclass Classification with Rejectioncited by 41
6 more
  1. 2020Calibrated Surrogate Losses for Adversarially Robust Classificationcited by 36
  2. 2021A Finer Calibration Analysis for Adversarial Robustnesscited by 26
  3. 2022Towards Consistency in Adversarial Classificationcited by 12
  4. 2019Online Active Learning of Reject Option Classifierscited by 9
  5. 2020ATRO: Adversarial Training with a Rejection Optioncited by 8
  6. 2023Stratified Adversarial Robustness with Rejectioncited by 4

Built on by

Not cited yet.