mlsanityData to 7 Oct 2026

Proper Network Interpretability Helps Adversarial Robustness in Classification

arXiv 2006.14748 ↗First posted 26 Jun 2020cs.LG stat.MLcited by 41

Not on the map. Why?

Abstract (arXiv)

Recent works have empirically shown that there exist adversarial examples that can be hidden from neural network interpretability (namely, making network interpretation maps visually similar), or interpretability is itself susceptible to adversarial attacks. In this paper, we theoretically show that with a proper measurement of interpretation, it is actually difficult to prevent prediction-evasion adversarial attacks from causing interpretation discrepancy, as confirmed by experiments on MNIST, CIFAR-10 and Restricted ImageNet. Spurred by that, we develop an interpretability-aware defensive scheme built only on promoting robust interpretation (without the need for resorting to adversarial loss minimization). We show that our defense achieves both robust classification and robust interpretation, outperforming state-of-the-art adversarial training methods against attacks of large perturbation in particular.

Key facts. Cited by 41 papers in the map (data through 7 Oct 2026). First posted on arXiv 26 Jun 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 9; 2022: 16; 2023: 4; 2024: 7; 2025: 4; 2026: 1.

41 papers.

Sort:

By area:

  1. 2022From Anecdotal Evidence to Quantitative Evaluation Methods: A Systematic Review on Evaluating Explainable AIcited by 299
  2. 2022Toward Transparent AI: A Survey on Interpreting the Inner Structures of Deep Neural Networkscited by 126
  3. 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 76
  4. 2025Archetypal SAE: Adaptive and Stable Dictionary Learning for Concept Extraction in Large Vision Modelscited by 67
  5. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  6. 2022Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysiscited by 38
  7. 2022Going Beyond XAI: A Systematic Survey for Explanation-Guided Learningcited by 35
  8. 2022Visual Prompting for Adversarial Robustnesscited by 33
  9. 2022Aligning Eyes between Humans and Deep Neural Network through Interactive Attention Alignmentcited by 27
  10. 2021Self-Interpretable Model with TransformationEquivariant Interpretationcited by 21
  11. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 17
  12. 2022Reverse Engineering of Imperceptible Adversarial Image Perturbationscited by 17
29 more
  1. 2021Fooling Partial Dependence via Data Poisoningcited by 16
  2. 2023Stability Guarantees for Feature Attributions with Multiplicative Smoothingcited by 14
  3. 2022Adversarial Training for Improving Model Robustness? Look at Both Prediction and Interpretationcited by 12
  4. 2021When and How to Fool Explainable Models (and Humans) with Adversarial Examplescited by 10
  5. 2021DI-AA: An Interpretable White-box Attack for Fooling Deep Neural Networkscited by 10
  6. 2022Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protectioncited by 6
  7. 2022On the explainable properties of 1-Lipschitz Neural Networks: An Optimal Transport Perspectivecited by 6
  8. 2025Superposition as Lossy Compression: Measure with Sparse Autoencoders and Connect to Adversarial Vulnerabilitycited by 6
  9. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  10. 2022Queried Unlabeled Data Improves and Robustifies Class-Incremental Learningcited by 4
  11. 2022Interpretations Cannot Be Trusted: Stealthy and Effective Adversarial Perturbations against Interpretable Deep Learningcited by 4
  12. 2023Improve Video Representation with Temporal Adversarial Augmentationcited by 3
  13. 2024Learning Minimal Neural Specificationscited by 3
  14. 2024Interpretability-Guided Test-Time Adversarial Defensecited by 3
  15. 2022Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification Systemcited by 2
  16. 2023A Practical Upper Bound for the Worst-Case Attribution Deviationscited by 2
  17. 2024Learning the irreversible progression trajectory of Alzheimer's diseasecited by 2
  18. 2024PASA: Attack Agnostic Unsupervised Adversarial Detection using Prediction & Attribution Sensitivity Analysiscited by 2
  19. 2025Factor Graph-based Interpretable Neural Networkscited by 2
  20. 2021The Definitions of Interpretability and Learning of Interpretable Modelscited by 1
  21. 2021Interpretability Aware Model Training to Improve Robustness against Out-of-Distribution Magnetic Resonance Images in Alzheimer's Disease Classificationcited by 1
  22. 2022PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attackcited by 1
  23. 2022Provable Robust Saliency-based Explanationscited by 1
  24. 2024Certified ℓ2 Attribution Robustness via Uniformly Smoothed Attributionscited by 1
  25. 2021A Unified Game-Theoretic Interpretation of Adversarial Robustnesscited by 0
  26. 2024Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscapecited by 0
  27. 2024Impact of Adversarial Attacks on Deep Learning Model Explainabilitycited by 0
  28. 2025Are Inherently Interpretable Models More Robust? A Study In Music Emotion Recognitioncited by 0
  29. 2026Representational Simplicity and Circuit Size Dissociate in a Threshold-Dependent Way: A Controlled Test via Adversarial Trainingcited by 0