mlsanityData to 7 Oct 2026

Removing Adversarial Noise in Class Activation Feature Space

arXiv 2104.09197 ↗First posted 19 Apr 2021cs.LGcited by 18

Not on the map. Why?

Abstract (arXiv)

Deep neural networks (DNNs) are vulnerable to adversarial noise. Preprocessing based defenses could largely remove adversarial noise by processing inputs. However, they are typically affected by the error amplification effect, especially in the front of continuously evolving attacks. To solve this problem, in this paper, we propose to remove adversarial noise by implementing a self-supervised adversarial training mechanism in a class activation feature space. To be specific, we first maximize the disruptions to class activation features of natural examples to craft adversarial examples. Then, we train a denoising model to minimize the distances between the adversarial examples and the natural examples in the class activation feature space. Empirical evaluations demonstrate that our method could significantly enhance adversarial robustness in comparison to previous state-of-the-art approaches, especially against unseen adversarial attacks and adaptive attacks.

Key facts. Cited by 18 papers in the map (data through 7 Oct 2026). Builds on 40 of its 49 references that are in the map. First posted on arXiv 19 Apr 2021.

Builds on

40 of 49 references.

References · 40

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Adam: A Method for Stochastic Optimizationcited by 36,960
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Mask R-CNNcited by 7,259
  6. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  8. 2013Intriguing properties of neural networkscited by 5,114
  9. 2016Wide Residual Networkscited by 3,057
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2014Sequence to Sequence Learning with Neural Networkscited by 2,974
  12. 2015Learning Deep Features for Discriminative Localizationcited by 2,430
28 more
  1. 2016Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Networkcited by 1,898
  2. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  3. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  4. 2017Grad-CAM++: Improved Visual Explanations for Deep Convolutional Networkscited by 936
  5. 2016Adversarial Machine Learning at Scalecited by 934
  6. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  7. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  8. 2017Countering Adversarial Images using Input Transformationscited by 517
  9. 2019Evading Defenses to Transferable Adversarial Examples by Translation-Invariant Attackscited by 440
  10. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  11. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 280
  12. 2017MagNet: a Two-Pronged Defense against Adversarial Examplescited by 268
  13. 2018The relativistic discriminator: a key element missing from standard GANcited by 234
  14. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  15. 2018Spatially Transformed Adversarial Examplescited by 195
  16. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 151
  17. 2014Towards Deep Neural Network Architectures Robust to Adversarial Examplescited by 146
  18. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  19. 2017Keeping the Bad Guys Out: Protecting and Vaccinating Deep Learning with JPEG Compressioncited by 86
  20. 2021Improving Adversarial Robustness via Channel-wise Activation Suppressingcited by 76
  21. 2019advertorch v0.1: An Adversarial Robustness Toolbox based on PyTorchcited by 69
  22. 2019Defending Against Physically Realizable Attacks on Image Classificationcited by 66
  23. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  24. 2018Motivating the Rules of the Game for Adversarial Example Researchcited by 57
  25. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  26. 2020Part-dependent Label Noise: Towards Instance-dependent Label Noisecited by 40
  27. 2020Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labelscited by 25
  28. 2020Stronger and Faster Wasserstein Adversarial Attackscited by 25

Built on by

Cited by year

Citing papers per year: 2021: 1; 2022: 3; 2023: 8; 2024: 5; 2025: 1.

18 papers.

Sort:

By area:

  1. 2024Defending Against Unforeseen Failure Modes with Latent Adversarial Trainingcited by 82
  2. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  3. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 16
  4. 2022Improving Adversarial Robustness via Mutual Information Estimationcited by 13
  5. 2021Modeling Adversarial Noise for Adversarial Trainingcited by 8
  6. 2024Robust Overfitting Does Matter: Test-Time Adversarial Purification With FGSMcited by 6
  7. 2024Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Trainingcited by 6
  8. 2022Perturbation Inactivation Based Adversarial Defense for Face Recognitioncited by 5
  9. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  10. 2023IDEA: Invariant Defense for Graph Adversarial Robustnesscited by 4
  11. 2022Strength-Adaptive Adversarial Trainingcited by 3
  12. 2024Artificial Immune System of Secure Face Recognition Against Adversarial Attackscited by 2
6 more
  1. 2025TAIGen: Training-Free Adversarial Image Generation via Diffusion Modelscited by 2
  2. 2023Rapid Plug-in Defenderscited by 1
  3. 2023Cybersecurity of AI medical devices: risks, legislation, and challengescited by 0
  4. 2023EMShepherd: Detecting Adversarial Samples via Side-channel Leakagecited by 0
  5. 2023Designing an attack-defense game: how to increase robustness of financial transaction models via a competitioncited by 0
  6. 2024Imperceptible Face Forgery Attack via Adversarial Semantic Maskcited by 0