mlsanityData to 7 Oct 2026

Towards Robust Explanations for Deep Neural Networks

arXiv 2012.10425 ↗First posted 18 Dec 2020cs.LGcited by 43

Not on the map. Why?

Abstract (arXiv)

Explanation methods shed light on the decision process of black-box classifiers such as deep neural networks. But their usefulness can be compromised because they are susceptible to manipulations. With this work, we aim to enhance the resilience of explanations. We develop a unified theoretical framework for deriving bounds on the maximal manipulability of a model. Based on these theoretical insights, we present three different techniques to boost robustness against manipulation: training with weight decay, smoothing activation functions, and minimizing the Hessian of the network. Our experimental results confirm the effectiveness of these approaches.

Key facts. Cited by 43 papers in the map (data through 7 Oct 2026). First posted on arXiv 18 Dec 2020.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 6; 2022: 15; 2023: 6; 2024: 10; 2025: 5; 2026: 1.

43 papers.

Sort:

By area:

  1. 2024AttnLRP: Attention-Aware Layer-Wise Relevance Propagation for Transformerscited by 116
  2. 2023Adversarial attacks and defenses in explainable artificial intelligence: A surveycited by 47
  3. 2021A Survey on the Robustness of Feature Importance and Counterfactual Explanationscited by 38
  4. 2024MambaLRP: Explaining Selective State Space Sequence Modelscited by 31
  5. 2022Diffeomorphic Counterfactuals with Generative Modelscited by 29
  6. 2022Investigating the fidelity of explainable artificial intelligence methods for applications of convolutional neural networks in geosciencecited by 28
  7. 2022SAFARI: Versatile and Efficient Evaluations for Robustness of Interpretabilitycited by 28
  8. 2024Decoupling Pixel Flipping and Occlusion Strategy for Consistent XAI Benchmarkscited by 28
  9. 2022Disentangled Explanations of Neural Network Predictions by Finding Relevant Subspacescited by 25
  10. 2022Robust Explanation Constraints for Neural Networkscited by 23
  11. 2022What Makes a Good Explanation?: A Harmonized View of Properties of Explanationscited by 21
  12. 2022Efficiently Training Low-Curvature Neural Networkscited by 19
31 more
  1. 2021Neural Network Attribution Methods for Problems in Geoscience: A Novel Synthetic Benchmark Datasetcited by 18
  2. 2021Explaining Bayesian Neural Networkscited by 18
  3. 2021Scrutinizing XAI using linear ground-truth data with suppressor variablescited by 18
  4. 2023On the Robustness of Removal-Based Feature Attributionscited by 18
  5. 2024Navigating the Maze of Explainable AI: A Systematic Approach to Evaluating Methods and Metricscited by 15
  6. 2021Visual explanation of black-box model: Similarity Difference and Uniqueness (SIDU) methodcited by 10
  7. 2024Regulating Model Reliance on Non-Robust Features by Smoothing Input Marginal Densitycited by 10
  8. 2022A.I. Robustness: a Human-Centered Perspective on Technological Challenges and Opportunitiescited by 8
  9. 2024SPES: Spectrogram Perturbation for Explainable Speech-to-Text Generationcited by 6
  10. 2021Self-learn to Explain Siamese Networks Robustlycited by 5
  11. 2022On the Robustness of Explanations of Deep Neural Network Models: A Surveycited by 5
  12. 2023Unveiling the Hessian's Connection to the Decision Boundarycited by 5
  13. 2023SmoothHess: ReLU Network Feature Interactions via Stein's Lemmacited by 5
  14. 2022Don't Get Me Wrong: How to Apply Deep Visual Interpretations to Time Seriescited by 4
  15. 2022Towards More Robust Interpretation via Local Gradient Alignmentcited by 4
  16. 2025Pixel-level Certified Explanations via Randomized Smoothingcited by 4
  17. 2022Robustness of Explanation Methods for NLP Modelscited by 3
  18. 2024Verified Training for Counterfactual Explanation Robustness under Data Shiftcited by 2
  19. 2025Factor Graph-based Interpretable Neural Networkscited by 2
  20. 2025Attribution Explanations for Deep Neural Networks: A Theoretical Perspectivecited by 2
  21. 2022Locally Invariant Explanations: Towards Stable and Unidirectional Explanations through Local Invariant Learningcited by 1
  22. 2022Provable Robust Saliency-based Explanationscited by 1
  23. 2023Overcoming Adversarial Attacks for Human-in-the-Loop Applicationscited by 1
  24. 2022Debiased-CAM to mitigate systematic error with faithful visual explanations of machine learningcited by 0
  25. 2023Robust Ranking Explanationscited by 0
  26. 2024Model-Agnostic Interpretation Framework in Machine Learning: A Comparative Study in NBA Sportscited by 0
  27. 2024Revealing Vulnerabilities of Neural Networks in Parameter Learning and Defense Against Explanation-Aware Backdoorscited by 0
  28. 2024Integrative CAM: Adaptive Layer Fusion for Comprehensive Interpretation of CNNscited by 0
  29. 2025Fixed Point Explainabilitycited by 0
  30. 2025Model Guidance via Robust Feature Attributioncited by 0
  31. 2026Improving Adversarial Robustness of Attribution via Implicit Regularizationcited by 0