mlsanityData to 14 Oct 2026

Modeling Adversarial Noise for Adversarial Training

arXiv 2109.09901 ↗First posted 21 Sep 2021cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

Deep neural networks have been demonstrated to be vulnerable to adversarial noise, promoting the development of defense against adversarial attacks. Motivated by the fact that adversarial noise contains well-generalizing features and that the relationship between adversarial data and natural data can help infer natural data and make reliable predictions, in this paper, we study to model adversarial noise by learning the transition relationship between adversarial labels (i.e. the flipped labels used to generate adversarial data) and natural labels (i.e. the ground truth labels of the natural data). Specifically, we introduce an instance-dependent transition matrix to relate adversarial labels and natural labels, which can be seamlessly embedded with the target model (enabling us to model stronger adaptive adversarial noise). Empirical evaluations demonstrate that our method could effectively improve adversarial accuracy.

Key facts. Cited by 8 papers in the map (data through 14 Oct 2026). Builds on 29 of its 39 references that are in the map. First posted on arXiv 21 Sep 2021.

Builds on

29 of 39 references.

References · 29

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  4. 2017Mask R-CNNcited by 7,277
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  6. 2013Intriguing properties of neural networkscited by 5,155
  7. 2016Wide Residual Networkscited by 3,070
  8. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  11. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
  12. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
17 more
  1. 2017Countering Adversarial Images using Input Transformationscited by 520
  2. 2017Feature Squeezing: Detecting Adversarial Examples in Deep Neural Networkscited by 486
  3. 2019Unlabeled Data Improves Adversarial Robustnesscited by 416
  4. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  5. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  6. 2019Are Anchor Points Really Indispensable in Label-Noise Learning?cited by 208
  7. 2018Spatially Transformed Adversarial Examplescited by 195
  8. 2020A Self-supervised Approach for Adversarial Robustnesscited by 180
  9. 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 153
  10. 2018Decoupling Direction and Norm for Efficient Gradient-Based L2 Adversarial Attacks and Defensescited by 109
  11. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  12. 2017MagNet and "Efficient Defenses Against Adversarial Attacks" are Not Robust to Adversarial Examplescited by 46
  13. 2020Class2Simi: A Noise Reduction Perspective on Learning with Noisy Labelscited by 25
  14. 2020Stronger and Faster Wasserstein Adversarial Attackscited by 25
  15. 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
  16. 2019On the Sensitivity of Adversarial Robustness to Input Data Distributionscited by 20
  17. 2021Removing Adversarial Noise in Class Activation Feature Spacecited by 18

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 4; 2024: 3.

8 papers.

  1. 2022Harnessing Out-Of-Distribution Examples via Augmenting Content and Stylecited by 43
  2. 2023On the Over-Memorization During Natural, Robust and Catastrophic Overfittingcited by 20
  3. 2023Survey on Adversarial Attack and Defense for Medical Image Analysis: Methods and Challengescited by 17
  4. 2024Layer-Aware Analysis of Catastrophic Overfitting: Revealing the Pseudo-Robust Shortcut Dependencycited by 10
  5. 2023Bridging Cross-task Protocol Inconsistency for Distillation in Dense Object Detectioncited by 6
  6. 2024Improving Accuracy-robustness Trade-off via Pixel Reweighted Adversarial Trainingcited by 6
  7. 2024Adversarial Training: A Surveycited by 6
  8. 2023Enhancing Robust Representation in Adversarial Training: Alignment and Exclusion Criteriacited by 0