mlsanityData to 7 Oct 2026

Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustness

arXiv 2112.00323 ↗First posted 1 Dec 2021cs.CVcited by 6

Not on the map. Why?

Abstract (arXiv)

In response to the threat of adversarial examples, adversarial training provides an attractive option for enhancing the model robustness by training models on online-augmented adversarial examples. However, most of the existing adversarial training methods focus on improving the robust accuracy by strengthening the adversarial examples but neglecting the increasing shift between natural data and adversarial examples, leading to a dramatic decrease in natural accuracy. To maintain the trade-off between natural and robust accuracy, we alleviate the shift from the perspective of feature adaption and propose a Feature Adaptive Adversarial Training (FAAT) optimizing the class-conditional feature adaption across natural data and adversarial examples. Specifically, we propose to incorporate a class-conditional discriminator to encourage the features become (1) class-discriminative and (2) invariant to the change of adversarial attacks. The novel FAAT framework enables the trade-off between natural and robust accuracy by generating features with similar distribution across natural and adversarial data, and achieve higher overall robustness benefited from the class-discriminative feature characteristics. Experiments on various datasets demonstrate that FAAT produces more discriminative features and performs favorably against state-of-the-art methods. Codes are available at https://github.com/VisionFlow/FAAT.

Key facts. Cited by 6 papers in the map (data through 7 Oct 2026). Builds on 43 of its 54 references that are in the map. First posted on arXiv 1 Dec 2021.

Builds on

43 of 54 references.

References · 43

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2013Intriguing properties of neural networkscited by 5,114
  4. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  5. 2014Unsupervised Domain Adaptation by Backpropagationcited by 1,906
  6. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2019Natural Adversarial Examplescited by 1,401
  9. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  10. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
  11. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  12. 2019Adversarial Training for Free!cited by 638
31 more
  1. 2018Improving Transferability of Adversarial Examples with Input Diversitycited by 591
  2. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  3. 2017Countering Adversarial Images using Input Transformationscited by 517
  4. 2019Contrastive Adaptation Network for Unsupervised Domain Adaptationcited by 407
  5. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  6. 2020Do Adversarially Robust ImageNet Models Transfer Better?cited by 315
  7. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  8. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  9. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  10. 2018Adversarial Logit Pairingcited by 224
  11. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  12. 2020Classes Matter: A Fine-grained Adversarial Approach to Cross-domain Semantic Segmentationcited by 142
  13. 2019Enhancing Adversarial Example Transferability with an Intermediate Level Attackcited by 139
  14. 2020Learnable Boundary Guided Adversarial Trainingcited by 93
  15. 2018Curriculum Adversarial Trainingcited by 89
  16. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 79
  17. 2020DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensemblescited by 73
  18. 2019Improving Adversarial Robustness of Ensembles with Diversity Trainingcited by 69
  19. 2019Adversarially robust transfer learningcited by 66
  20. 2019Efficient Adversarial Training with Transferable Adversarial Examplescited by 54
  21. 2021Adversarial Robustness under Long-Tailed Distributioncited by 50
  22. 2020Once-for-All Adversarial Training: In-Situ Tradeoff between Robustness and Accuracy for Freecited by 48
  23. 2021Consistency Regularization for Adversarial Robustnesscited by 42
  24. 2020Invisible Perturbations: Physical Adversarial Examples Exploiting the Rolling Shutter Effectcited by 40
  25. 2020Over-the-Air Adversarial Flickering Attacks against Video Recognition Networkscited by 35
  26. 2020Adversarial Feature Desensitizationcited by 12
  27. 2021Improving Model Robustness with Latent Distribution Locally and Globallycited by 9
  28. 2021CARTL: Cooperative Adversarially-Robust Transfer Learningcited by 8
  29. 2021Domain Invariant Adversarial Learningcited by 7
  30. 2020Adversarial Defense by Latent Style Transformationscited by 3
  31. 2021Adaptive Feature Alignment for Adversarial Trainingcited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2023: 1; 2024: 3; 2025: 1; 2026: 1.

6 papers.

  1. 2025Failure Cases Are Better Learned But Boundary Says Sorry: Facilitating Smooth Perception Change for Accuracy-Robustness Trade-Off in Adversarial Trainingcited by 2
  2. 2024MEAT: Median-Ensemble Adversarial Training for Improving Robustness and Generalizationcited by 1
  3. 2023Releasing Inequality Phenomenon in ℓ∞-norm Adversarial Training via Input Gradient Distillationcited by 0
  4. 2024Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalizationcited by 0
  5. 2024Improving Fast Adversarial Training Paradigm: An Example Taxonomy Perspectivecited by 0
  6. 2026Robust Alignment: Harmonizing Clean Accuracy and Adversarial Robustness in Adversarial Trainingcited by 0