mlsanityData to 14 Oct 2026

Threat of Adversarial Attacks on Deep Learning in Computer Vision: A Survey

arXiv 1801.00553 ↗First posted 2 Jan 2018cs.CVcited by 460

Not on the map. Why?

Cited by 21 in LLM safety and security, but placed by its own abstract, which didn’t fit.

Abstract (arXiv)

Deep learning is at the heart of the current rise of machine learning and artificial intelligence. In the field of Computer Vision, it has become the workhorse for applications ranging from self-driving cars to surveillance and security. Whereas deep neural networks have demonstrated phenomenal success (often beyond human capabilities) in solving complex problems, recent studies show that they are vulnerable to adversarial attacks in the form of subtle perturbations to inputs that lead a model to predict incorrect outputs. For images, such perturbations are often too small to be perceptible, yet they completely fool the deep learning models. Adversarial attacks pose a serious threat to the success of deep learning in practice. This fact has lead to a large influx of contributions in this direction. This article presents the first comprehensive survey on adversarial attacks on deep learning in Computer Vision. We review the works that design adversarial attacks, analyze the existence of such attacks and propose defenses against them. To emphasize that adversarial attacks are possible in practical conditions, we separately review the contributions that evaluate adversarial attacks in the real-world scenarios. Finally, we draw on the literature to provide a broader outlook of the research direction.

Key facts. Cited by 460 papers in the map (data through 14 Oct 2026). First posted on arXiv 2 Jan 2018.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2021: 146; 2022: 91; 2023: 103; 2024: 56; 2025: 39; 2026: 25.

460 papers.

Sort:

By area:

  1. 2021Generalized Out-of-Distribution Detection: A Surveycited by 802
  2. 2021Recent Advances in Adversarial Training for Adversarial Robustnesscited by 279
  3. 2023Large Language Model Alignment: A Surveycited by 243
  4. 2021Gradient-based Adversarial Attacks against Text Transformerscited by 234
  5. 2021Trustworthy AI: From Principles to Practicescited by 207
  6. 2023Raising the Cost of Malicious AI-Powered Image Editingcited by 163
  7. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  8. 2024Black-Box Access is Insufficient for Rigorous AI Auditscited by 126
  9. 2021Trustworthy AI: A Computational Perspectivecited by 93
  10. 2021PointCutMix: Regularization Strategy for Point Cloud Classificationcited by 69
  11. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  12. 2023How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defensescited by 66
38 more
  1. 2024Risk Taxonomy, Mitigation, and Assessment Benchmarks of Large Language Model Systemscited by 66
  2. 2021This Looks Like That... Does it? Shortcomings of Latent Space Prototype Interpretability in Deep Networkscited by 65
  3. 2021A Survey On Universal Adversarial Attackcited by 59
  4. 2021Relating Adversarially Robust Generalization to Flat Minimacited by 57
  5. 2021Adversarial Robustness Comparison of Vision Transformer and MLP-Mixer to CNNscited by 57
  6. 2021Deep Gait Recognition: A Surveycited by 54
  7. 2021Can stable and accurate neural networks be computed? -- On the barriers of deep learning and Smale's 18th problemcited by 53
  8. 2021Adversarial Example Detection for DNN Models: A Review and Experimental Comparisoncited by 52
  9. 2021Exploring Counterfactual Explanations Through the Lens of Adversarial Examples: A Theoretical and Empirical Analysiscited by 52
  10. 2022Visual Speech-Aware Perceptual 3D Facial Expression Reconstruction from Videoscited by 50
  11. 2021Targeted Attack against Deep Neural Networks via Flipping Limited Weight Bitscited by 49
  12. 2022Patch-Fool: Are Vision Transformers Always Robust Against Adversarial Perturbations?cited by 49
  13. 2021A Systematic Review of Robustness in Deep Learning for Computer Vision: Mind the gap?cited by 48
  14. 2023An Empirical Study of Pre-Trained Model Reuse in the Hugging Face Deep Learning Model Registrycited by 47
  15. 2021Single Node Injection Attack against Graph Neural Networkscited by 45
  16. 2021Reveal of Vision Transformers Robustness against Adversarial Attackscited by 43
  17. 2022Efficient Adversarial Training without Attacking: Worst-Case-Aware Robust Reinforcement Learningcited by 43
  18. 2022On the Robustness of Safe Reinforcement Learning under Observational Perturbationscited by 38
  19. 2022Multi-Objective Hyperparameter Optimization in Machine Learning -- An Overviewcited by 37
  20. 2023Improving Human-AI Collaboration With Descriptions of AI Behaviorcited by 36
  21. 2021Physical Adversarial Attacks on an Aerial Imagery Object Detectorcited by 35
  22. 2024Adversarial Attacks and Defenses on Text-to-Image Diffusion Models: A Surveycited by 35
  23. 2023DeceptPrompt: Exploiting LLM-driven Code Generation via Adversarial Natural Language Instructionscited by 33
  24. 2024Attacks and Defenses for Generative Diffusion Models: A Comprehensive Surveycited by 32
  25. 2023ACTIVE: Towards Highly Transferable 3D Physical Camouflage for Universal and Robust Vehicle Evasioncited by 31
  26. 2021Deep Learning-Based Autonomous Driving Systems: A Survey of Attacks and Defensescited by 30
  27. 2022Green Learning: Introduction, Examples and Outlookcited by 30
  28. 2021Drawing Robust Scratch Tickets: Subnetworks with Inborn Robustness Are Found within Randomly Initialized Networkscited by 29
  29. 2022Large-scale Robustness Analysis of Video Action Recognition Modelscited by 29
  30. 2023Large Language Models of Code Fail at Completing Code with Potential Bugscited by 29
  31. 2021CAMERAS: Enhanced Resolution And Sanity preserving Class Activation Mapping for image saliencycited by 28
  32. 2022Phantom Sponges: Exploiting Non-Maximum Suppression to Attack Deep Object Detectorscited by 28
  33. 2022Gradient Methods Provably Converge to Non-Robust Networkscited by 27
  34. 2021BASAR:Black-box Attack on Skeletal Action Recognitioncited by 26
  35. 20213D Adversarial Attacks Beyond Point Cloudcited by 26
  36. 2021TkML-AP: Adversarial Attacks to Top-k Multi-Label Learningcited by 26
  37. 2021Adversarial Attacks on Deep Models for Financial Transaction Recordscited by 24
  38. 2022A Survey of Adversarial Defences and Robustness in NLPcited by 23

50 most cited of 460 All 460 (JSON)