mlsanityData to 7 Oct 2026

Improving Interpretability via Regularization of Neural Activation Sensitivity

arXiv 2211.08686 ↗First posted 16 Nov 2022cs.LG cs.CR cs.CVcited by 5

Not on the map. Why?

Abstract (arXiv)

State-of-the-art deep neural networks (DNNs) are highly effective at tackling many real-world tasks. However, their wide adoption in mission-critical contexts is hampered by two major weaknesses - their susceptibility to adversarial attacks and their opaqueness. The former raises concerns about the security and generalization of DNNs in real-world conditions, whereas the latter impedes users' trust in their output. In this research, we (1) examine the effect of adversarial robustness on interpretability and (2) present a novel approach for improving the interpretability of DNNs that is based on regularization of neural activation sensitivity. We evaluate the interpretability of models trained using our method to that of standard models and models trained using state-of-the-art adversarial robustness techniques. Our results show that adversarially robust models are superior to standard models and that models trained using our proposed method are even better than adversarially robust models in terms of interpretability.

Key facts. Cited by 5 papers in the map (data through 7 Oct 2026). Builds on 39 of its 60 references that are in the map. First posted on arXiv 16 Nov 2022.

Builds on

39 of 60 references.

References · 39

  1. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2016Densely Connected Convolutional Networkscited by 6,691
  5. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  6. 2017A Unified Approach to Interpreting Model Predictionscited by 6,488
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2016"Why Should I Trust You?": Explaining the Predictions of Any Classifiercited by 5,040
  9. 2017Axiomatic Attribution for Deep Networkscited by 3,350
  10. 2016Identity Mappings in Deep Residual Networkscited by 1,960
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  12. 2017SmoothGrad: removing noise by adding noisecited by 1,097
27 more
  1. 2016Adversarial Machine Learning at Scalecited by 934
  2. 2018Robustness May Be at Odds with Accuracycited by 873
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  4. 2017Adversarial Examples Are Not Easily Detected: Bypassing Ten Detection Methodscited by 542
  5. 2020Captum: A unified and generic model interpretability library for PyTorchcited by 542
  6. 2018Explaining Explanations: An Overview of Interpretability of Machine Learningcited by 508
  7. 2018Towards Robust Interpretability with Self-Explaining Neural Networkscited by 505
  8. 2017Decision-Based Adversarial Attacks: Reliable Attacks Against Black-Box Machine Learning Modelscited by 459
  9. 2017Methods for Interpreting and Understanding Deep Neural Networkscited by 342
  10. 2019HopSkipJumpAttack: A Query-Efficient Decision-Based Attackcited by 328
  11. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  12. 2018On the Robustness of Interpretability Methodscited by 310
  13. 2019On the (In)fidelity and Sensitivity for Explanationscited by 309
  14. 2017Detecting Adversarial Samples from Artifactscited by 244
  15. 2017PixelDefend: Leveraging Generative Models to Understand and Defend against Adversarial Examplescited by 243
  16. 2017On Detecting Adversarial Perturbationscited by 232
  17. 2020Evaluating and Aggregating Feature-based Model Explanationscited by 185
  18. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  19. 2022Quantus: An Explainable AI Toolkit for Responsible Evaluation of Neural Network Explanations and Beyondcited by 171
  20. 2019Robust Learning with Jacobian Regularizationcited by 127
  21. 2020Feature Purification: How Adversarial Training Performs Robust Deep Learningcited by 107
  22. 2018Improving DNN Robustness to Adversarial Attacks using Jacobian Regularizationcited by 88
  23. 2019Interpreting Adversarially Trained Convolutional Neural Networkscited by 75
  24. 2019When Explainability Meets Adversarial Learning: Detecting Adversarial Examples using SHAP Signaturescited by 40
  25. 2020Reviewing the Need for Explainable Artificial Intelligence (xAI)cited by 29
  26. 2020Improving Interpretability in Medical Imaging Diagnosis using Adversarial Trainingcited by 9
  27. 2018Detecting Adversarial Perturbations Through Spatial Behavior in Activation Spacescited by 4

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 2; 2025: 1; 2026: 1.

5 papers.

  1. 2023Studying How to Efficiently and Effectively Guide Models with Explanationscited by 16
  2. 2024Interpret Your Decision: Logical Reasoning Regularization for Generalization in Visual Classificationcited by 5
  3. 2025GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Modelscited by 2
  4. 2026Securing Time Integrity in Energy IoT Against Clock Drift and Y2K38 Failurescited by 1
  5. 2024Smooth InfoMax -- Towards Easier Post-Hoc Interpretabilitycited by 0