mlsanityData to 7 Oct 2026

Towards Deep Learning Models Resistant to Adversarial Attacks

arXiv 1706.06083 ↗First posted 19 Jun 2017stat.ML cs.LG cs.NEcited by 6,326

Not on the map. Why?

Cited by 374 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Recent work has demonstrated that deep neural networks are vulnerable to adversarial examples---inputs that are almost indistinguishable from natural data and yet classified incorrectly by the network. In fact, some of the latest findings suggest that the existence of adversarial attacks may be an inherent weakness of deep learning models. To address this problem, we study the adversarial robustness of neural networks through the lens of robust optimization. This approach provides us with a broad and unifying view on much of the prior work on this topic. Its principled nature also enables us to identify methods for both training and attacking neural networks that are reliable and, in a certain sense, universal. In particular, they specify a concrete security guarantee that would protect against any adversary. These methods let us train networks with significantly improved resistance to a wide range of adversarial attacks. They also suggest the notion of security against a first-order adversary as a natural and broad security guarantee. We believe that robustness against such well-defined classes of adversaries is an important stepping stone towards fully resistant deep learning models. Code and pre-trained models are available at https://github.com/MadryLab/mnist_challenge and https://github.com/MadryLab/cifar10_challenge.

Key facts. Cited by 6,326 papers in the map (data through 7 Oct 2026). First posted on arXiv 19 Jun 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 1; 2019: 0; 2020: 0; 2021: 1090; 2022: 1135; 2023: 1177; 2024: 1162; 2025: 1036; 2026: 725.

6,326 papers.

Sort:

By area:

  1. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  2. 2023The Rise and Potential of Large Language Model Based Agents: A Surveycited by 1,422
  3. 2024HarmBench: A Standardized Evaluation Framework for Automated Red Teaming and Robust Refusalcited by 1,330
  4. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  5. 2022Diffusion Models: A Comprehensive Survey of Methods and Applicationscited by 1,107
  6. 2021Learning to Prompt for Continual Learningcited by 938
  7. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  8. 2021Robust fine-tuning of zero-shot modelscited by 785
  9. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
  10. 2022Diffusion Models for Adversarial Purificationcited by 469
  11. 2024Jailbreaking Leading Safety-Aligned LLMs with Simple Adaptive Attackscited by 450
  12. 2021Intriguing Properties of Vision Transformerscited by 446
38 more
  1. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  2. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attackscited by 434
  3. 2023Detecting Language Model Attacks with Perplexitycited by 411
  4. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrationscited by 401
  5. 2023A Survey on Large Language Model (LLM) Security and Privacy: The Good, the Bad, and the Uglycited by 380
  6. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  7. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 307
  8. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  9. 2023Are aligned neural networks adversarially aligned?cited by 305
  10. 2024Improving Alignment and Robustness with Circuit Breakerscited by 302
  11. 2021Unsolved Problems in ML Safetycited by 291
  12. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  13. 2021Distribution-Free, Risk-Controlling Prediction Setscited by 278
  14. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  15. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 260
  16. 2021When Vision Transformers Outperform ResNets without Pre-training or Strong Data Augmentationscited by 259
  17. 2021Global Filter Networks for Image Classificationcited by 257
  18. 2021Deep Generative Modelling: A Comparative Review of VAEs, GANs, Normalizing Flows, Energy-Based and Autoregressive Modelscited by 251
  19. 2021Understanding Robustness of Transformers for Image Classificationcited by 250
  20. 2021Accuracy on the Line: On the Strong Correlation Between Out-of-Distribution and In-Distribution Generalizationcited by 248
  21. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  22. 2024Rethinking Machine Unlearning for Large Language Modelscited by 247
  23. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  24. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 233
  25. 2021Improving Robustness using Generated Datacited by 233
  26. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 226
  27. 2021Beta-CROWN: Efficient Bound Propagation with Per-neuron Split Constraints for Complete and Incomplete Neural Network Robustness Verificationcited by 224
  28. 2021Fast Yet Effective Machine Unlearningcited by 209
  29. 2021Vision Transformers are Robust Learnerscited by 208
  30. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  31. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  32. 2021Learning to Optimize: A Primer and A Benchmarkcited by 206
  33. 2021Trustworthy AI: From Principles to Practicescited by 206
  34. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  35. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Nowcited by 204
  36. 2023Data-centric Artificial Intelligence: A Surveycited by 202
  37. 2021Fixing Data Augmentation to Improve Adversarial Robustnesscited by 201
  38. 2021Data Augmentation Can Improve Robustnesscited by 193

50 most cited of 6,326 All 6,326 (JSON)