mlsanityData to 14 Oct 2026

Robustness Feature Adapter for Efficient Adversarial Training

arXiv 2508.17680 ↗First posted 25 Aug 2025cs.LG cs.AI cs.CVcited by 2

Not on the map. Why?

Abstract (arXiv)

Adversarial training (AT) with projected gradient descent is the most popular method to improve model robustness under adversarial attacks. However, computational overheads become prohibitively large when AT is applied to large backbone models. AT is also known to have the issue of robust overfitting. This paper contributes to solving both problems simultaneously towards building more trustworthy foundation models. In particular, we propose a new adapter-based approach for efficient AT directly in the feature space. We show that the proposed adapter-based approach can improve the inner-loop convergence quality by eliminating robust overfitting. As a result, it significantly increases computational efficiency and improves model accuracy by generalizing adversarial robustness to unseen attacks. We demonstrate the effectiveness of the new adapter-based approach in different backbone architectures and in AT at scale.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Builds on 42 of its 55 references that are in the map. First posted on arXiv 25 Aug 2025.

Builds on

42 of 55 references.

References · 42

  1. 2020Denoising Diffusion Probabilistic Modelscited by 21,076
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  3. 2015Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shiftcited by 7,005
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  5. 2020Training data-efficient image transformers & distillation through attentioncited by 4,586
  6. 2019Parameter-Efficient Transfer Learning for NLPcited by 4,236
  7. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,998
  8. 2020Supervised Contrastive Learningcited by 2,829
  9. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
  10. 2018A Simple Unified Framework for Detecting Out-of-Distribution Samples and Adversarial Attackscited by 1,485
  11. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  12. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,268
30 more
  1. 2016Least Squares Generative Adversarial Networkscited by 1,001
  2. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 953
  3. 2020Fast is better than free: Revisiting adversarial trainingcited by 727
  4. 2019Adversarial Training for Free!cited by 643
  5. 2020Overfitting in adversarially robust deep learningcited by 506
  6. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  7. 2018Characterizing Adversarial Subspaces Using Local Intrinsic Dimensionalitycited by 282
  8. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  9. 2017Detecting Adversarial Samples from Artifactscited by 245
  10. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 243
  11. 2021Improving Robustness using Generated Datacited by 234
  12. 2020Understanding and Improving Fast Adversarial Trainingcited by 214
  13. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 208
  14. 2018Lipschitz-Margin Training: Scalable Certification of Perturbation Invariance for Deep Neural Networkscited by 195
  15. 2021Towards Robust Vision Transformercited by 137
  16. 2021On the Convergence and Robustness of Adversarial Trainingcited by 130
  17. 2022Robustness and Accuracy Could Be Reconcilable by (Proper) Definitioncited by 111
  18. 2023AdvCLIP: Downstream-agnostic Adversarial Examples in Multimodal Contrastive Learningcited by 103
  19. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  20. 2023Decoupled Kullback-Leibler Divergence Losscited by 58
  21. 2017APE-GAN: Adversarial Perturbation Elimination with GANcited by 57
  22. 2021Boosting Fast Adversarial Training with Learnable Adversarial Initializationcited by 40
  23. 2024Revisiting Adversarial Training at Scalecited by 33
  24. 2021Towards Defending against Adversarial Examples via Attack-Invariant Featurescited by 25
  25. 2022Revisiting adapters with adversarial trainingcited by 18
  26. 2023Balance, Imbalance, and Rebalance: Understanding Robust Overfitting from a Minimax Game Perspectivecited by 18
  27. 2022Improving Adversarial Robustness by Putting More Regularizations on Less Robust Samplescited by 11
  28. 2023Adventures of Trustworthy Vision-Language Models: A Surveycited by 10
  29. 2021BulletTrain: Accelerating Robust Neural Network Training via Boundary Example Miningcited by 8
  30. 2024Classifier Guidance Enhances Diffusion-based Adversarial Purification by Preserving Predictive Informationcited by 5

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026What Makes VLMs Robust? Towards Reconciling Robustness and Accuracy in Vision-Language Modelscited by 0
  2. 2026Recti-Q: Feature-Space Rectification for Out-of-Distribution-Robust Quantized Perception in Edge Roboticscited by 0