mlsanityData to 14 Oct 2026

Adversarial Examples: Attacks and Defenses for Deep Learning

arXiv 1712.07107 ↗First posted 19 Dec 2017cs.LG cs.CR cs.CVcited by 351

Not on the map. Why?

Abstract (arXiv)

With rapid progress and significant successes in a wide spectrum of applications, deep learning is being applied in many safety-critical environments. However, deep neural networks have been recently found vulnerable to well-designed input samples, called adversarial examples. Adversarial examples are imperceptible to human but can easily fool deep neural networks in the testing/deploying stage. The vulnerability to adversarial examples becomes one of the major risks for applying deep neural networks in safety-critical environments. Therefore, attacks and defenses on adversarial examples draw great attention. In this paper, we review recent findings on adversarial examples for deep neural networks, summarize the methods for generating adversarial examples, and propose a taxonomy of these methods. Under the taxonomy, applications for adversarial examples are investigated. We further elaborate on countermeasures for adversarial examples and explore the challenges and the potential solutions.

Key facts. Cited by 351 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Dec 2017.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 114; 2022: 79; 2023: 55; 2024: 50; 2025: 32; 2026: 21.

351 papers.

Sort:

By area:

  1. 2023Baseline Defenses for Adversarial Attacks Against Aligned Language Modelscited by 651
  2. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  3. 2023LLM Self Defense: By Self Examination, LLMs Know They Are Being Trickedcited by 244
  4. 2021Trustworthy AI: From Principles to Practicescited by 207
  5. 2021A Unified Survey on Anomaly, Novelty, Open-Set, and Out-of-Distribution Detection: Solutions and Future Challengescited by 154
  6. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  7. 2021Truthful AI: Developing and governing AI that does not liecited by 113
  8. 2022CommonsenseQA 2.0: Exposing the Limits of AI through Gamificationcited by 109
  9. 2022FedPrompt: Communication-Efficient and Privacy Preserving Prompt Tuning in Federated Learningcited by 91
  10. 2024A Survey of Attacks on Large Vision-Language Models: Resources, Advances, and Future Trendscited by 84
  11. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  12. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
38 more
  1. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  2. 2021Socially Responsible AI Algorithms: Issues, Purposes, and Challengescited by 56
  3. 2024Explainable AI for Safe and Trustworthy Autonomous Driving: A Systematic Reviewcited by 53
  4. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  5. 2022Membership Inference Attacks and Defenses in Neural Network Pruningcited by 45
  6. 2022A Survey of Robust Adversarial Training in Pattern Recognition: Fundamental, Theory, and Methodologiescited by 44
  7. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  8. 20213D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detectioncited by 43
  9. 2021Improved Text Classification via Contrastive Adversarial Trainingcited by 38
  10. 2023Self-Influence Guided Data Reweighting for Language Model Pre-trainingcited by 37
  11. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
  12. 2023A Survey on ChatGPT: AI-Generated Contents, Challenges, and Solutionscited by 35
  13. 2024Machine Unlearning: A Comprehensive Surveycited by 35
  14. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 30
  15. 2021Pay attention to your loss: understanding misconceptions about 1-Lipschitz neural networkscited by 30
  16. 2021DetectorGuard: Provably Securing Object Detectors against Localized Patch Hiding Attackscited by 29
  17. 2021A Review of Adversarial Attack and Defense for Classification Methodscited by 29
  18. 2025A Survey on Autonomy-Induced Security Risks in Large Model-Based Agentscited by 29
  19. 2021Corner Case Generation and Analysis for Safety Assessment of Autonomous Vehiclescited by 27
  20. 2021IPLS : A Framework for Decentralized Federated Learningcited by 26
  21. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  22. 2021A Survey on Open Set Recognitioncited by 25
  23. 2022A Survey on Physical Adversarial Attack in Computer Visioncited by 25
  24. 2021Adversarial Attacks on Deep Models for Financial Transaction Recordscited by 24
  25. 2021ARM-Net: Adaptive Relation Modeling Network for Structured Datacited by 24
  26. 2021Evaluating Adversarial Attacks on Driving Safety in Vision-Based Autonomous Vehiclescited by 24
  27. 2021DNNV: A Framework for Deep Neural Network Verificationcited by 23
  28. 2021Indicators of Attack Failure: Debugging and Improving Optimization of Adversarial Examplescited by 23
  29. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 23
  30. 2024Adversarial Attacks of Vision Tasks in the Past 10 Years: A Surveycited by 23
  31. 2022Overparameterized Linear Regression under Adversarial Attackscited by 21
  32. 2021Fighting Gradients with Gradients: Dynamic Defenses against Adversarial Attackscited by 20
  33. 2022Pixle: a fast and effective black-box attack based on rearranging pixelscited by 20
  34. 2022Watermark Vaccine: Adversarial Attacks to Prevent Watermark Removalcited by 20
  35. 2023Efficient Robustness Assessment via Adversarial Spatial-Temporal Focus on Videoscited by 20
  36. 2021Poisoning Attacks on Fair Machine Learningcited by 19
  37. 2022POLICE: Provably Optimal Linear Constraint Enforcement for Deep Neural Networkscited by 19
  38. 2024Generative Unlearning for Any Identitycited by 19

50 most cited of 351 All 351 (JSON)