mlsanityData to 7 Oct 2026

A Finer Calibration Analysis for Adversarial Robustness

arXiv 2105.01550 ↗First posted 4 May 2021cs.LG stat.MLcited by 26

Not on the map. Why?

Abstract (arXiv)

We present a more general analysis of H-calibration for adversarially robust classification. By adopting a finer definition of calibration, we can cover settings beyond the restricted hypothesis sets studied in previous work. In particular, our results hold for most common hypothesis sets used in machine learning. We both fix some previous calibration results (Bao et al., 2020) and generalize others (Awasthi et al., 2021). Moreover, our calibration results, combined with the previous study of consistency by Awasthi et al. (2021), also lead to more general H-consistency results covering common hypothesis sets.

Key facts. Cited by 26 papers in the map (data through 7 Oct 2026). Builds on 12 of its 19 references that are in the map. First posted on arXiv 4 May 2021.

Builds on

12 of 19 references.

References · 12

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  6. 2018Robustness May Be at Odds with Accuracycited by 873
  7. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  8. 2019Adversarial Training for Free!cited by 638
  9. 2018Rademacher Complexity for Adversarially Robust Generalizationcited by 132
  10. 2020Adversarial Learning Guarantees for Linear Hypotheses and Neural Networkscited by 47
  11. 2021Calibration and Consistency of Adversarial Surrogate Lossescited by 47
  12. 2020Calibrated Surrogate Losses for Adversarially Robust Classificationcited by 36

Built on by

Cited by year

Citing papers per year: 2022: 2; 2023: 9; 2024: 9; 2025: 6.

26 papers.

Sort:

  1. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  2. 2023Predictor-Rejector Multi-Class Abstention: Theoretical Analysis and Algorithmscited by 36
  3. 2023Learning to Reject with a Fixed Predictor: Application to Decontextualizationcited by 32
  4. 2023Theoretically Grounded Loss Functions and Algorithms for Score-Based Multi-Class Abstentioncited by 32
  5. 2024Regression with Multi-Expert Deferralcited by 29
  6. 2023Ranking with Abstentioncited by 27
  7. 2023In Defense of Softmax Parametrization for Calibrated and Consistent Learning to Defercited by 26
  8. 2024Realizable H-Consistent and Bayes-Consistent Loss Functions for Learning to Defercited by 26
  9. 2024A Universal Growth Rate for Learning with Smooth Surrogate Lossescited by 24
  10. 2024Cardinality-Aware Set Prediction and Top-k Classificationcited by 23
  11. 2024Multi-Label Learning with Stronger Consistency Guaranteescited by 22
  12. 2024H-Consistency Guarantees for Regressioncited by 21
14 more
  1. 2024Enhanced H-Consistency Boundscited by 18
  2. 2025Mastering Multiple-Expert Routing: Realizable H-Consistency and Strong Guarantees for Learning to Defercited by 16
  3. 2025Balancing the Scales: A Theoretical and Algorithmic Framework for Learning from Imbalanced Datacited by 15
  4. 2022Towards Consistency in Adversarial Classificationcited by 12
  5. 2025Budgeted Multiple-Expert Deferralcited by 11
  6. 2025Improved Balanced Classification with Theoretically Grounded Loss Functionscited by 9
  7. 2023The Adversarial Consistency of Surrogate Risks for Binary Classificationcited by 6
  8. 2025Principled Algorithms for Optimizing Generalized Metrics in Binary Classificationcited by 6
  9. 2022The Consistency of Adversarial Training for Binary Classificationcited by 3
  10. 2023Non-Asymptotic Bounds for Adversarial Excess Risk under Misspecified Modelscited by 2
  11. 2024Adversarial Consistency and the Uniqueness of the Adversarial Bayes Classifiercited by 2
  12. 2023On Achieving Optimal Adversarial Test Errorcited by 1
  13. 2025Contrasting Cost-Agnostic and Cost-Sensitive Losses under Limited Model Capacity via mathcal H-consistencycited by 1
  14. 2024Towards Calibrated Losses for Adversarial Robust Reject Option Classificationcited by 0