mlsanityData to 7 Oct 2026

Recent Advances in Adversarial Training for Adversarial Robustness

arXiv 2102.01356 ↗First posted 2 Feb 2021cs.LG cs.AI cs.CRcited by 276

Not on the map. Why?

Abstract (arXiv)

Adversarial training is one of the most effective approaches defending against adversarial examples for deep learning models. Unlike other defense strategies, adversarial training aims to promote the robustness of models intrinsically. During the last few years, adversarial training has been studied and discussed from various aspects. A variety of improvements and developments of adversarial training are proposed, which were, however, neglected in existing surveys. For the first time in this survey, we systematically review the recent progress on adversarial training for adversarial robustness with a novel taxonomy. Then we discuss the generalization problems in adversarial training from three perspectives. Finally, we highlight the challenges which are not fully tackled and present potential future directions.

Key facts. Cited by 276 papers in the map (data through 7 Oct 2026). Builds on 89 of its 130 references that are in the map. First posted on arXiv 2 Feb 2021.

Builds on

89 of 130 references.

References · 89

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2017mixup: Beyond Empirical Risk Minimizationcited by 5,155
  4. 2013Intriguing properties of neural networkscited by 5,114
  5. 2016Adversarial examples in the physical worldcited by 1,762
  6. 2017Improved Regularization of Convolutional Neural Networks with Cutoutcited by 1,623
  7. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  8. 2019Adversarial Examples Are Not Bugs, They Are Featurescited by 950
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2016Practical Black-Box Attacks against Machine Learningcited by 893
  11. 2018Robustness May Be at Odds with Accuracycited by 873
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 833
38 more
  1. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  2. 2019Adversarial Training for Free!cited by 638
  3. 2017Countering Adversarial Images using Input Transformationscited by 517
  4. 2019Using Self-Supervised Learning Can Improve Model Robustness and Uncertaintycited by 511
  5. 2020Overfitting in adversarially robust deep learningcited by 504
  6. 2018Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Surveycited by 459
  7. 2018Generalizing to Unseen Domains via Adversarial Data Augmentationcited by 451
  8. 2018Generating Natural Language Adversarial Examplescited by 422
  9. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  10. 2019Using Pre-Training Can Improve Model Robustness and Uncertaintycited by 373
  11. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 350
  12. 2017Defense against Adversarial Attacks Using High-Level Representation Guided Denoisercited by 329
  13. 2018Adversarially Robust Generalization Requires More Datacited by 318
  14. 2017Adversarial Attacks on Neural Network Policiescited by 314
  15. 2018Adversarial Attack on Graph Structured Datacited by 300
  16. 2020Learning to Learn Single Domain Generalizationcited by 295
  17. 2014Identifying and attacking the saddle point problem in high-dimensional non-convex optimizationcited by 286
  18. 2017Adversarial Examples for Semantic Segmentation and Object Detectioncited by 275
  19. 2018Audio Adversarial Examples: Targeted Attacks on Speech-to-Textcited by 268
  20. 2020Attacks Which Do Not Kill Training Make Adversarial Learning Strongercited by 242
  21. 2017Improving the Adversarial Robustness and Interpretability of Deep Neural Networks by Regularizing their Input Gradientscited by 236
  22. 2018Adversarial Logit Pairingcited by 224
  23. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  24. 2020Understanding and Improving Fast Adversarial Trainingcited by 213
  25. 2020Bag of Tricks for Adversarial Trainingcited by 199
  26. 2019Adversarial Training and Robustness for Multiple Perturbationscited by 182
  27. 2019You Only Propagate Once: Accelerating Adversarial Training via Maximal Principlecited by 181
  28. 2018Robustness via curvature regularization, and vice versacited by 174
  29. 2018Disentangling Adversarial Robustness and Generalizationcited by 171
  30. 2018MMA Training: Direct Input Space Margin Maximization through Adversarial Trainingcited by 171
  31. 2019Are Labels Required for Improving Adversarial Robustness?cited by 162
  32. 2017The Space of Transferable Adversarial Examplescited by 156
  33. 2017Robust Deep Reinforcement Learning with Adversarial Attackscited by 152
  34. 2019Adversarial Robustness through Local Linearizationcited by 146
  35. 2020Robust Pre-Training by Adversarial Contrastive Learningcited by 144
  36. 2020Adversarial Self-Supervised Contrastive Learningcited by 138
  37. 2018Is Robustness the Cost of Accuracy? -- A Comprehensive Study on the Robustness of 18 Deep Image Classification Modelscited by 135
  38. 2018Rademacher Complexity for Adversarially Robust Generalizationcited by 132

50 most cited of 89 All 89 (JSON)

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 17; 2022: 37; 2023: 82; 2024: 63; 2025: 52; 2026: 25.

276 papers.

Sort:

By area:

  1. 2023Trustworthy LLMs: a Survey and Guideline for Evaluating Large Language Models' Alignmentcited by 394
  2. 2024LLM Maybe LongLM: Self-Extend LLM Context Window Without Tuningcited by 133
  3. 2023Receler: Reliable Concept Erasing of Text-to-Image Diffusion Models via Lightweight Eraserscited by 118
  4. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 88
  5. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  6. 2023Generative Pre-trained Transformer: A Comprehensive Review on Enabling Technologies, Potential Applications, Emerging Challenges, and Future Directionscited by 55
  7. 2024Vitron: A Unified Pixel-level Vision LLM for Understanding, Generating, Segmenting, Editingcited by 49
  8. 2023Neural Polarizer: A Lightweight and Effective Backdoor Defense via Purifying Poisoned Featurescited by 35
  9. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 34
  10. 2022Explainable Deep Learning Methods in Medical Image Classification: A Surveycited by 31
  11. 2023ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editingcited by 30
  12. 2022Benchmarking Adversarially Robust Quantum Machine Learning at Scalecited by 28
38 more
  1. 2022HOTCOLD Block: Fooling Thermal Infrared Detectors with a Novel Wearable Designcited by 27
  2. 2023Towards quantum enhanced adversarial robustness in machine learningcited by 26
  3. 2021Black-box Adversarial Attacks on Commercial Speech Platforms with Minimal Informationcited by 25
  4. 2022Threat Model-Agnostic Adversarial Defense using Diffusion Modelscited by 24
  5. 2022AI Security for Geoscience and Remote Sensing: Challenges and Future Trendscited by 23
  6. 2025CLIP is Strong Enough to Fight Back: Test-time Counterattacks towards Zero-shot Adversarial Robustness of CLIPcited by 23
  7. 2022The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Trainingcited by 22
  8. 2023Towards Viewpoint-Invariant Visual Recognition via Adversarial Trainingcited by 19
  9. 2023Improving the Accuracy-Robustness Trade-Off of Classifiers via Adaptive Smoothingcited by 18
  10. 2023Fake News Detectors are Biased against Texts Generated by Large Language Modelscited by 18
  11. 2023MimicDiffusion: Purifying Adversarial Perturbation via Mimicking Clean Diffusion Modelcited by 18
  12. 2021Invariant Policy Learning: A Causal Perspectivecited by 17
  13. 2022Zero-Query Transfer Attacks on Context-Aware Object Detectorscited by 17
  14. 2023Regularization properties of adversarially-trained linear regressioncited by 17
  15. 2026Lying with Truths: Open-Channel Multi-Agent Collusion for Belief Manipulation via Generative Montagecited by 17
  16. 2021Reliability Assessment and Safety Arguments for Machine Learning Components in System Assurancecited by 16
  17. 2024Manipulation Facing Threats: Evaluating Physical Vulnerabilities in End-to-End Vision Language Action Modelscited by 16
  18. 2022Detecting Adversarial Perturbations in Multi-Task Perceptioncited by 15
  19. 2022Do Perceptually Aligned Gradients Imply Adversarial Robustness?cited by 15
  20. 2023The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attackscited by 15
  21. 2024Estimating the Probabilities of Rare Outputs in Language Modelscited by 15
  22. 2022Recent Advances in Neural Text Generation: A Task-Agnostic Surveycited by 14
  23. 2023Understanding and Improving Ensemble Adversarial Defensecited by 14
  24. 2025Enhancing CLIP Robustness via Cross-Modality Alignmentcited by 14
  25. 2022RoPGen: Towards Robust Code Authorship Attribution via Automatic Coding Style Transformationcited by 13
  26. 2022Blackbox Attacks via Surrogate Ensemble Searchcited by 13
  27. 2023Flow-based Distributionally Robust Optimizationcited by 13
  28. 2022Why adversarial training can hurt robust accuracycited by 12
  29. 2022ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotationcited by 12
  30. 2022Defense Against Adversarial Attacks on Audio DeepFake Detectioncited by 12
  31. 2023On the Importance of Backbone to the Adversarial Robustness of Object Detectorscited by 12
  32. 2024Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuningcited by 12
  33. 2025Robustness in Large Language Models: A Survey of Mitigation Strategies and Evaluation Metricscited by 12
  34. 2021Assessing the Reliability of Deep Learning Classifiers Through Robustness Evaluation and Operational Profilescited by 11
  35. 2023Certified Robust Neural Networks: Generalization and Corruption Resistancecited by 11
  36. 2023Adversarial Infrared Blocks: A Multi-view Black-box Attack to Thermal Infrared Detectors in Physical Worldcited by 11
  37. 2024On the Robustness of Kolmogorov-Arnold Networks: An Adversarial Perspectivecited by 11
  38. 2024Trustworthy Federated Learning: Privacy, Security, and Beyondcited by 11

50 most cited of 276 All 276 (JSON)