mlsanityData to 7 Oct 2026

Efficient Adversarial Training with Transferable Adversarial Examples

arXiv 1912.11969 ↗First posted 27 Dec 2019cs.LG cs.CVcited by 54

Not on the map. Why?

Abstract (arXiv)

Adversarial training is an effective defense method to protect classification models against adversarial attacks. However, one limitation of this approach is that it can require orders of magnitude additional training time due to high cost of generating strong adversarial examples during training. In this paper, we first show that there is high transferability between models from neighboring epochs in the same training process, i.e., adversarial examples from one epoch continue to be adversarial in subsequent epochs. Leveraging this property, we propose a novel method, Adversarial Training with Transferable Adversarial Examples (ATTA), that can enhance the robustness of trained models and greatly improve the training efficiency by accumulating adversarial perturbations through epochs. Compared to state-of-the-art adversarial training methods, ATTA enhances adversarial accuracy by up to 7.2% on CIFAR10 and requires 12~14x less training time on MNIST and CIFAR10 datasets with comparable model robustness.

Key facts. Cited by 54 papers in the map (data through 7 Oct 2026). First posted on arXiv 27 Dec 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 13; 2022: 15; 2023: 17; 2024: 5; 2025: 3; 2026: 1.

54 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 75
  3. 2022SegPGD: An Effective and Efficient Adversarial Attack for Evaluating and Boosting Segmentation Robustnesscited by 74
  4. 2023Shared Adversarial Unlearning: Backdoor Mitigation by Unlearning Shared Adversarial Examplescited by 40
  5. 2022Fast Adversarial Training with Adaptive Step Sizecited by 24
  6. 2021Meta Adversarial Training against Universal Patchescited by 19
  7. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  8. 2022REAP: A Large-Scale Realistic Adversarial Patch Benchmarkcited by 17
  9. 2023Revisiting and Exploring Efficient Fast Adversarial Training via LAW: Lipschitz Regularization and Auto Weight Averagingcited by 14
  10. 2021Group-wise Inhibition based Feature Regularization for Robust Classificationcited by 11
  11. 2021On the Impact of Hard Adversarial Instances on Overfitting in Adversarial Trainingcited by 11
  12. 2022Robust Real-World Image Super-Resolution against Adversarial Attackscited by 11
38 more
  1. 2021Robustness through Data Augmentation Loss Consistencycited by 8
  2. 2023FedRight: An Effective Model Copyright Protection for Federated Learningcited by 8
  3. 2021Push Stricter to Decide Better: A Class-Conditional Feature Adaptive Framework for Improving Adversarial Robustnesscited by 6
  4. 2022SRoUDA: Meta Self-training for Robust Unsupervised Domain Adaptationcited by 6
  5. 2023Leveraging Hierarchical Feature Sharing for Efficient Dataset Condensationcited by 6
  6. 2024Adversarial Training: A Surveycited by 6
  7. 2021All You Need is RAW: Defending Against Adversarial Attacks with Camera Image Pipelinescited by 5
  8. 2022Robust Binary Models by Pruning Randomly-initialized Networkscited by 5
  9. 2023Investigating Catastrophic Overfitting in Fast Adversarial Training: A Self-fitting Perspectivecited by 5
  10. 2023Adversarial Attacks and Defenses in Machine Learning-Powered Networks: A Contemporary Surveycited by 5
  11. 2023Universal Adversarial Defense in Remote Sensing Based on Pre-trained Denoising Diffusion Modelscited by 5
  12. 2022Revisiting Outer Optimization in Adversarial Trainingcited by 4
  13. 2022Random Walks for Adversarial Meshescited by 3
  14. 2022Adversarial Attacks on Speech Recognition Systems for Mission-Critical Applications: A Surveycited by 3
  15. 2022A Girl Has A Name, And It's ... Adversarial Authorship Attribution for Deobfuscationcited by 3
  16. 2022Batch Normalization Is Blind to the First and Second Derivatives of the Losscited by 3
  17. 2023Hard Adversarial Example Mining for Improving Robust Fairnesscited by 3
  18. 2023Raze to the Ground: Query-Efficient Adversarial HTML Attacks on Machine-Learning Phishing Webpage Detectorscited by 3
  19. 20213D Point Cloud Completion with Geometric-Aware Adversarial Augmentationcited by 2
  20. 2021Adversarial Attack across Datasetscited by 2
  21. 2022Robust Representation via Dynamic Feature Aggregationcited by 2
  22. 2023Mixing Classifiers to Alleviate the Accuracy-Robustness Trade-Offcited by 2
  23. 2024Improving Fast Adversarial Training via Self-Knowledge Guidancecited by 2
  24. 2025GenoArmory: A Unified Evaluation Framework for Adversarial Attacks on Genomic Foundation Modelscited by 2
  25. 2021Meta Adversarial Perturbationscited by 1
  26. 2022Improving the Robustness and Generalization of Deep Neural Network with Confidence Threshold Reductioncited by 1
  27. 2023Intrinsic Biologically Plausible Adversarial Robustnesscited by 1
  28. 2023The Hidden Adversarial Vulnerabilities of Medical Federated Learningcited by 1
  29. 2024TF-Attack: Transferable and Fast Adversarial Attacks on Large Language Modelscited by 1
  30. 2021Robustifying ℓ_∞ Adversarial Training to the Union of Perturbation Modelscited by 0
  31. 2021Enhanced countering adversarial attacks via input denoising and feature restoringcited by 0
  32. 2022Gradient Aligned Attacks via a Few Queriescited by 0
  33. 2022FACM: Intermediate Layer Still Retain Effective Features against Adversarial Examplescited by 0
  34. 2023A Spectral Perspective towards Understanding and Improving Adversarial Robustnesscited by 0
  35. 2023Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgetscited by 0
  36. 2023Omnipotent Adversarial Training in the Wildcited by 0
  37. 2023Universal Pyramid Adversarial Training for Improved ViT Performancecited by 0
  38. 2024Towards Trustworthy Unsupervised Domain Adaptation: A Representation Learning Perspective for Enhancing Robustness, Discrimination, and Generalizationcited by 0

50 most cited of 54 All 54 (JSON)