mlsanityData to 7 Oct 2026

Adversarial Machine Learning at Scale

arXiv 1611.01236 ↗First posted 4 Nov 2016cs.CV cs.CR cs.LGcited by 934

Not on the map. Why?

Cited by 23 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Adversarial examples are malicious inputs designed to fool machine learning models. They often transfer from one model to another, allowing attackers to mount black box attacks without knowledge of the target model's parameters. Adversarial training is the process of explicitly training a model on adversarial examples, in order to make it more robust to attack or to reduce its test error on clean inputs. So far, adversarial training has primarily been applied to small problems. In this research, we apply adversarial training to ImageNet. Our contributions include: (1) recommendations for how to succesfully scale adversarial training to large models and datasets, (2) the observation that adversarial training confers robustness to single-step attack methods, (3) the finding that multi-step attack methods are somewhat less transferable than single-step attack methods, so single-step attacks are the best for mounting black-box attacks, and (4) resolution of a "label leaking" effect that causes adversarially trained models to perform better on adversarial examples than on clean examples, because the adversarial example construction process uses the true label and the model can learn to exploit regularities in the construction process.

Key facts. Cited by 934 papers in the map (data through 7 Oct 2026). First posted on arXiv 4 Nov 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 257; 2022: 211; 2023: 177; 2024: 162; 2025: 97; 2026: 30.

934 papers.

Sort:

By area:

  1. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  2. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  3. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 260
  4. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  5. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  6. 2022Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detectioncited by 172
  7. 2022LIFT: Language-Interfaced Fine-Tuning for Non-Language Machine Learning Taskscited by 146
  8. 2022Understanding The Robustness in Vision Transformerscited by 144
  9. 2021Anti-Adversarially Manipulated Attributions for Weakly and Semi-Supervised Semantic Segmentationcited by 134
  10. 2021Adversarial purification with Score-based generative modelscited by 132
  11. 2022Frequency Domain Model Augmentation for Adversarial Attackcited by 128
  12. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
38 more
  1. 2021Feature Importance-aware Transferable Adversarial Attackscited by 125
  2. 20223D Common Corruptions and Data Augmentationcited by 120
  3. 2024Dissecting Adversarial Robustness of Multimodal LM Agentscited by 118
  4. 2021Uncertainty-aware Joint Salient Object and Camouflaged Object Detectioncited by 114
  5. 2021On the Adversarial Robustness of Vision Transformerscited by 104
  6. 2021Re-imagining Algorithmic Fairness in India and Beyondcited by 102
  7. 2022LAS-AT: Adversarial Training with Learnable Attack Strategycited by 94
  8. 2023Diffusion Models for Imperceptible and Transferable Adversarial Attackcited by 93
  9. 2023Rethinking Model Ensemble in Transfer-based Adversarial Attackscited by 88
  10. 2024Enhancing Noise Robustness of Retrieval-Augmented Language Models with Adaptive Adversarial Trainingcited by 88
  11. 2023A Comprehensive Study on Robustness of Image Classification Models: Benchmarking and Rethinkingcited by 85
  12. 2021Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferabilitycited by 84
  13. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 82
  14. 2021Towards Transferable Adversarial Attacks on Vision Transformerscited by 80
  15. 2021Revisiting and Advancing Fast Adversarial Training Through The Lens of Bi-Level Optimizationcited by 75
  16. 2023Unleashing the potential of prompt engineering for large language modelscited by 72
  17. 2024HyperSIGMA: Hyperspectral Intelligence Comprehension Foundation Modelcited by 72
  18. 2023VLATTACK: Multimodal Adversarial Attacks on Vision-Language Tasks via Pre-trained Modelscited by 66
  19. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 65
  20. 2024Visual-RolePlay: Universal Jailbreak Attack on MultiModal Large Language Models via Role-playing Image Charactercited by 61
  21. 2021A Survey On Universal Adversarial Attackcited by 59
  22. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  23. 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
  24. 2021Exploring Memorization in Adversarial Trainingcited by 55
  25. 2024Don't Say No: Jailbreaking LLM by Suppressing Refusalcited by 53
  26. 2021Fooling thermal infrared pedestrian detectors in real world using small bulbscited by 51
  27. 2022Predicting Out-of-Distribution Error with the Projection Normcited by 50
  28. 2021How Should Pre-Trained Language Models Be Fine-Tuned Towards Adversarial Robustness?cited by 49
  29. 2022Towards Robust Rain Removal Against Adversarial Attacks: A Comprehensive Benchmark Analysis and Beyondcited by 48
  30. 2021Adversarially Guided Actor-Criticcited by 47
  31. 2021Boosting Randomized Smoothing with Variance Reduced Classifierscited by 47
  32. 2021OOD-CV: A Benchmark for Robustness to Out-of-Distribution Shifts of Individual Nuisances in Natural Imagescited by 46
  33. 2021Online Adversarial Purification based on Self-Supervisioncited by 45
  34. 2023A Survey on Segment Anything Model (SAM): Vision Foundation Model Meets Prompt Engineeringcited by 45
  35. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  36. 2023How Smooth Is Attention?cited by 44
  37. 2024Steering Away from Harm: An Adaptive Approach to Defending Vision Language Model Against Jailbreakscited by 44
  38. 2022Eliciting and Learning with Soft Labels from Every Annotatorcited by 43

50 most cited of 934 All 934 (JSON)