mlsanityData to 7 Oct 2026

Interpretability-Guided Test-Time Adversarial Defense

arXiv 2409.15190 ↗First posted 23 Sep 2024cs.CV cs.CR cs.LGcited by 3

Not on the map. Why?

Abstract (arXiv)

We propose a novel and low-cost test-time adversarial defense by devising interpretability-guided neuron importance ranking methods to identify neurons important to the output classes. Our method is a training-free approach that can significantly improve the robustness-accuracy tradeoff while incurring minimal computational overhead. While being among the most efficient test-time defenses (4x faster), our method is also robust to a wide range of black-box, white-box, and adaptive attacks that break previous test-time defenses. We demonstrate the efficacy of our method for CIFAR10, CIFAR100, and ImageNet-1k on the standard RobustBench benchmark (with average gains of 2.6%, 4.9%, and 2.8% respectively). We also show improvements (average 1.5%) over the state-of-the-art test-time defenses even under strong adaptive attacks.

Key facts. Cited by 3 papers in the map (data through 7 Oct 2026). Builds on 48 of its 59 references that are in the map. First posted on arXiv 23 Sep 2024.

Builds on

48 of 59 references.

References · 48

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  3. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  4. 2014ImageNet Large Scale Visual Recognition Challengecited by 8,441
  5. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  6. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  7. 2016Wide Residual Networkscited by 3,057
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  9. 2013Visualizing and Understanding Convolutional Networkscited by 2,278
  10. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  12. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
36 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  2. 2017Network Dissection: Quantifying Interpretability of Deep Visual Representationscited by 703
  3. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  4. 2020RobustBench: a standardized adversarial robustness benchmarkcited by 659
  5. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  6. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  7. 2020Understanding the Role of Individual Units in a Deep Neural Networkcited by 254
  8. 2020Compositional Explanations of Neuronscited by 172
  9. 2022CLIP-Dissect: Automatic Description of Neuron Representations in Deep Vision Networkscited by 144
  10. 2020To be Robust or to be Fair: Towards Fairness in Adversarial Trainingcited by 137
  11. 2022Natural Language Descriptions of Deep Visual Featurescited by 136
  12. 2021Adversarial purification with Score-based generative modelscited by 132
  13. 2020RayS: A Ray Searching Method for Hard-label Adversarial Attackcited by 94
  14. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  15. 2021Stable Neural ODE with Lyapunov-Stable Equilibrium Points for Defending Against Adversarial Attackscited by 91
  16. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  17. 2022Evaluating the Adversarial Robustness of Adaptive Test-time Defensescited by 64
  18. 2020Guided Adversarial Attack for Evaluating and Enhancing Adversarial Defensescited by 61
  19. 2023CFA: Class-wise Calibrated Fair Adversarial Trainingcited by 53
  20. 2019Enhancing Adversarial Defense by k-Winners-Take-Allcited by 51
  21. 2021Adversarial Attacks are Reversible with Natural Supervisioncited by 47
  22. 2021Online Adversarial Purification based on Self-Supervisioncited by 45
  23. 2022Efficient and Effective Augmentation Strategy for Adversarial Trainingcited by 43
  24. 2020Proper Network Interpretability Helps Adversarial Robustness in Classificationcited by 41
  25. 2020A Tunable Robust Pruning Framework Through Dynamic Network Rewiring of DNNscited by 37
  26. 2021Attacking Adversarial Attacks as A Defensecited by 31
  27. 2021Combating Adversaries with Anti-Adversariescited by 27
  28. 2020Importance-Driven Deep Learning System Testingcited by 24
  29. 2021Towards Robust Neural Networks via Close-loop Controlcited by 23
  30. 2022Scaling Adversarial Training to Large Perturbation Boundscited by 20
  31. 2024Linear Explanations for Individual Neuronscited by 19
  32. 2022NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networkscited by 17
  33. 2020On Saliency Maps and Adversarial Robustnesscited by 11
  34. 2021AID-Purifier: A Light Auxiliary Network for Boosting Adversarial Defensecited by 10
  35. 2024Interpreting Neurons in Deep Vision Networks with Language Modelscited by 10
  36. 2018Attention, Please! Adversarial Defense via Activation Rectification and Preservationcited by 4

Built on by

Cited by year (2026 to 7 Oct)

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

3 papers.

  1. 2025One Surrogate to Fool Them All: Universal, Transferable, and Targeted Adversarial Attacks with CLIPcited by 15
  2. 2025Interpretable and Steerable Concept Bottleneck Sparse Autoencoderscited by 6
  3. 2026A Provable Energy-Guided Test-Time Defense Boosting Adversarial Robustness of Large Vision-Language Modelscited by 1