mlsanityData to 14 Oct 2026

Robust Attribution Regularization

arXiv 1905.09957 ↗First posted 23 May 2019cs.LG cs.AI cs.CRcited by 47

Not on the map. Why?

Abstract (arXiv)

An emerging problem in trustworthy machine learning is to train models that produce robust interpretations for their predictions. We take a step towards solving this problem through the lens of axiomatic attribution of neural networks. Our theory is grounded in the recent work, Integrated Gradients (IG), in axiomatically attributing a neural network's output change to its input change. We propose training objectives in classic robust optimization models to achieve robust IG attributions. Our objectives give principled generalizations of previous objectives designed for robust predictions, and they naturally degenerate to classic soft-margin training for one-layer neural networks. We also generalize previous theory and prove that the objectives for different robust optimization models are closely related. Experiments demonstrate the effectiveness of our method, and also point to intriguing problems which hint at the need for better optimization techniques or better neural network architectures for robust attribution training.

Key facts. Cited by 47 papers in the map (data through 14 Oct 2026). First posted on arXiv 23 May 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 8; 2022: 15; 2023: 10; 2024: 7; 2025: 4; 2026: 3.

47 papers.

Sort:

By area:

  1. 2021When Does Contrastive Learning Preserve Adversarial Robustness from Pretraining to Finetuning?cited by 77
  2. 2022Beyond Explaining: Opportunities and Challenges of XAI-Based Model Improvementcited by 48
  3. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 48
  4. 2021Fast Axiomatic Attribution for Neural Networkscited by 35
  5. 2023TANGOS: Regularizing Tabular Neural Networks through Gradient Orthogonalization and Specializationcited by 32
  6. 2021NoiseGrad: Enhancing Explanations by Introducing Stochasticity to Model Weightscited by 28
  7. 2022Robust Explanation Constraints for Neural Networkscited by 24
  8. 2022What Makes a Good Explanation?: A Harmonized View of Properties of Explanationscited by 22
  9. 2021Robust Models Are More Interpretable Because Attributions Look Normalcited by 21
  10. 2021On the Lack of Robust Interpretability of Neural Text Classifierscited by 17
  11. 2021Show or Suppress? Managing Input Uncertainty in Machine Learning Model Explanationscited by 15
  12. 2023Are Data-driven Explanations Robust against Out-of-distribution Data?cited by 14
35 more
  1. 2024DEAL: Disentangle and Localize Concept-level Explanations for VLMscited by 14
  2. 2022Fooling Explanations in Text Classifierscited by 13
  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. 2023BadVFL: Backdoor Attacks in Vertical Federated Learningcited by 10
  6. 2024Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Densitycited by 10
  7. 2023It Is All About Data: A Survey on the Effects of Data on Adversarial Robustnesscited by 9
  8. 2022Exploiting the Relationship Between Kendall's Rank Correlation and Cosine Similarity for Attribution Protectioncited by 6
  9. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  10. 2022Towards More Robust Interpretation via Local Gradient Alignmentcited by 4
  11. 2023AttributionLab: Faithfulness of Feature Attribution Under Controllable Environmentscited by 3
  12. 2023Rethinking Robustness of Model Attributionscited by 3
  13. 2026Attribution-Guided Model Rectification of Unreliable Neural Network Behaviorscited by 3
  14. 2021More Than Words: Towards Better Quality Interpretations of Text Classifierscited by 2
  15. 2022Saliency Guided Adversarial Training for Learning Generalizable Features with Applications to Medical Imaging Classification Systemcited by 2
  16. 2022Identifying the Source of Vulnerability in Explanation Discrepancy: A Case Study in Neural Text Classificationcited by 2
  17. 2023A Practical Upper Bound for the Worst-Case Attribution Deviationscited by 2
  18. 2024Combining Machine Learning Defenses without Conflictscited by 2
  19. 2025Factor Graph-based Interpretable Neural Networkscited by 2
  20. 2022Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learningcited by 1
  21. 2022Verifying Attention Robustness of Deep Neural Networks against Semantic Perturbationscited by 1
  22. 2022PointACL:Adversarial Contrastive Learning for Robust Point Clouds Representation under Adversarial Attackcited by 1
  23. 2022Estimating the Adversarial Robustness of Attributions in Text with Transformerscited by 1
  24. 2022Provable Robust Saliency-based Explanationscited by 1
  25. 2023DARE: Towards Robust Text Explanations in Biomedical and Healthcare Applicationscited by 1
  26. 2024Certified ℓ2 Attribution Robustness via Uniformly Smoothed Attributionscited by 1
  27. 2026Explanation-Guided Adversarial Training for Robust and Interpretable Modelscited by 1
  28. 2023Robust Ranking Explanationscited by 0
  29. 2024Are Classification Robustness and Explanation Robustness Really Strongly Correlated? An Analysis Through Input Loss Landscapecited by 0
  30. 2024Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoorscited by 0
  31. 2024Impact of Adversarial Attacks on Deep Learning Model Explainabilitycited by 0
  32. 2025Fixed Point Explainabilitycited by 0
  33. 2025Accuracy is Not Enough: Poisoning Interpretability in Federated Learning via Color Skewcited by 0
  34. 2025Rethinking Robustness: A New Approach to Evaluating Feature Attribution Methodscited by 0
  35. 2026WisdomNet: trustable machine learning toward error-free classificationcited by 0