mlsanityData to 7 Oct 2026

Explaining and Harnessing Adversarial Examples

arXiv 1412.6572 ↗First posted 20 Dec 2014stat.ML cs.LGcited by 7,287

Not on the map. Why?

Cited by 304 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Several machine learning models, including neural networks, consistently misclassify adversarial examples---inputs formed by applying small but intentionally worst-case perturbations to examples from the dataset, such that the perturbed input results in the model outputting an incorrect answer with high confidence. Early attempts at explaining this phenomenon focused on nonlinearity and overfitting. We argue instead that the primary cause of neural networks' vulnerability to adversarial perturbation is their linear nature. This explanation is supported by new quantitative results while giving the first explanation of the most intriguing fact about them: their generalization across architectures and training sets. Moreover, this view yields a simple and fast method of generating adversarial examples. Using this approach to provide examples for adversarial training, we reduce the test set error of a maxout network on the MNIST dataset.

Key facts. Cited by 7,287 papers in the map (data through 7 Oct 2026). First posted on arXiv 20 Dec 2014.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 4; 2019: 0; 2020: 1; 2021: 1442; 2022: 1377; 2023: 1378; 2024: 1274; 2025: 1073; 2026: 738.

7,287 papers.

Sort:

By area:

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,456
  2. 2023Universal and Transferable Adversarial Attacks on Aligned Language Modelscited by 2,914
  3. 2023Jailbreaking Black Box Large Language Models in Twenty Queriescited by 1,326
  4. 2022Red Teaming Language Models with Language Modelscited by 983
  5. 2021Blended Diffusion for Text-driven Editing of Natural Imagescited by 924
  6. 2021Generalized Out-of-Distribution Detection: A Surveycited by 796
  7. 2021Domain Generalization: A Surveycited by 760
  8. 2020Aligning AI With Shared Human Valuescited by 706
  9. 2021FLAVA: A Foundational Language And Vision Alignment Modelcited by 646
  10. 2021Offline Reinforcement Learning as One Big Sequence Modeling Problemcited by 636
  11. 2023Tree of Attacks: Jailbreaking Black-Box LLMs Automaticallycited by 619
  12. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 608
38 more
  1. 2022Diffusion Models for Adversarial Purificationcited by 469
  2. 2021Intriguing Properties of Vision Transformerscited by 446
  3. 2018Scalable agent alignment via reward modeling: a research directioncited by 438
  4. 2023SmoothLLM: Defending Large Language Models Against Jailbreaking Attackscited by 434
  5. 2023Detecting Language Model Attacks with Perplexitycited by 411
  6. 2023Jailbreak and Guard Aligned Language Models with Only Few In-Context Demonstrationscited by 401
  7. 2023Can AI-Generated Text be Reliably Detected?cited by 372
  8. 2021Rethinking Spatial Dimensions of Vision Transformerscited by 361
  9. 2021On the Importance of Gradients for Detecting Distributional Shifts in the Wildcited by 338
  10. 2022A Holistic Approach to Undesired Content Detection in the Real Worldcited by 337
  11. 2018Reward learning from human preferences and demonstrations in Ataricited by 314
  12. 2021Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networkscited by 313
  13. 2022The Effects of Reward Misspecification: Mapping and Mitigating Misaligned Modelscited by 312
  14. 2023Visual Adversarial Examples Jailbreak Aligned Large Language Modelscited by 307
  15. 2021Membership Inference Attacks on Machine Learning: A Surveycited by 306
  16. 2023The Stable Signature: Rooting Watermarks in Latent Diffusion Modelscited by 289
  17. 2023On Evaluating Adversarial Robustness of Large Vision-Language Modelscited by 281
  18. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 276
  19. 2023Jailbreak in pieces: Compositional Adversarial Attacks on Multi-Modal Language Modelscited by 260
  20. 2021Global Filter Networks for Image Classificationcited by 257
  21. 2021Understanding Robustness of Transformers for Image Classificationcited by 250
  22. 2023Certifying LLM Safety against Adversarial Promptingcited by 248
  23. 2021Enhancing the Transferability of Adversarial Attacks through Variance Tuningcited by 242
  24. 2021Improving Robustness using Generated Datacited by 233
  25. 2021ConSERT: A Contrastive Framework for Self-Supervised Sentence Representation Transfercited by 231
  26. 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 230
  27. 2021Adversarial GLUE: A Multi-Task Benchmark for Robustness Evaluation of Language Modelscited by 227
  28. 2024Adjoint Matching: Fine-tuning Flow and Diffusion Generative Models with Memoryless Stochastic Optimal Controlcited by 222
  29. 2023PromptRobust: Towards Evaluating the Robustness of Large Language Models on Adversarial Promptscited by 218
  30. 2022SpaText: Spatio-Textual Representation for Controllable Image Generationcited by 217
  31. 2021Fast Yet Effective Machine Unlearningcited by 209
  32. 2023On the Robustness of ChatGPT: An Adversarial and Out-of-distribution Perspectivecited by 208
  33. 2021Towards Causal Representation Learningcited by 207
  34. 2023Better Diffusion Models Further Improve Adversarial Trainingcited by 207
  35. 2021Trustworthy AI: From Principles to Practicescited by 206
  36. 2023Cross-Entropy Loss Functions: Theoretical Analysis and Applicationscited by 206
  37. 2023To Generate or Not? Safety-Driven Unlearned Diffusion Models Are Still Easy To Generate Unsafe Images ... For Nowcited by 204
  38. 2021Hidden Killer: Invisible Textual Backdoor Attacks with Syntactic Triggercited by 203

50 most cited of 7,287 All 7,287 (JSON)