mlsanityData to 14 Oct 2026

Beyond Vulnerabilities: A Survey of Adversarial Attacks as Both Threats and Defenses in Computer Vision Systems

arXiv 2508.01845 ↗First posted 3 Aug 2025cs.CV cs.AI cs.CRcited by 4

Not on the map. Why?

Abstract (arXiv)

Adversarial attacks against computer vision systems have emerged as a critical research area that challenges the fundamental assumptions about neural network robustness and security. This comprehensive survey examines the evolving landscape of adversarial techniques, revealing their dual nature as both sophisticated security threats and valuable defensive tools. We provide a systematic analysis of adversarial attack methodologies across three primary domains: pixel-space attacks, physically realizable attacks, and latent-space attacks. Our investigation traces the technical evolution from early gradient-based methods such as FGSM and PGD to sophisticated optimization techniques incorporating momentum, adaptive step sizes, and advanced transferability mechanisms. We examine how physically realizable attacks have successfully bridged the gap between digital vulnerabilities and real-world threats through adversarial patches, 3D textures, and dynamic optical perturbations. Additionally, we explore the emergence of latent-space attacks that leverage semantic structure in internal representations to create more transferable and meaningful adversarial examples. Beyond traditional offensive applications, we investigate the constructive use of adversarial techniques for vulnerability assessment in biometric authentication systems and protection against malicious generative models. Our analysis reveals critical research gaps, particularly in neural style transfer protection and computational efficiency requirements. This survey contributes a comprehensive taxonomy, evolution analysis, and identification of future research directions, aiming to advance understanding of adversarial vulnerabilities and inform the development of more robust and trustworthy computer vision systems.

Key facts. Cited by 4 papers in the map (data through 14 Oct 2026). Builds on 106 of its 162 references that are in the map. First posted on arXiv 3 Aug 2025.

Builds on

106 of 162 references.

References · 106

  1. 2015Deep Residual Learning for Image Recognitioncited by 52,096
  2. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
  4. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,177
  5. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  6. 2014Explaining and Harnessing Adversarial Examplescited by 7,364
  7. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  8. 2013Intriguing properties of neural networkscited by 5,155
  9. 2022DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generationcited by 3,300
  10. 2016Adversarial examples in the physical worldcited by 1,769
  11. 2016Practical Black-Box Attacks against Machine Learningcited by 903
  12. 2017Ensemble Adversarial Training: Attacks and Defensescited by 840
38 more
  1. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 685
  2. 2018Turning Your Weakness Into a Strength: Watermarking Deep Neural Networks by Backdooringcited by 357
  3. 2019Nesterov Accelerated Gradient and Scale Invariance for Adversarial Attackscited by 355
  4. 2017Adversarial Examples: Attacks and Defenses for Deep Learningcited by 351
  5. 2019Adversarial Attacks and Defenses in Images, Graphs and Text: A Reviewcited by 237
  6. 2023Sequential Modeling Enables Scalable Learning for Large Vision Modelscited by 212
  7. 2020Media Forensics and DeepFakes: an overviewcited by 209
  8. 2023Adversarial Example Does Good: Preventing Painting Imitation from Diffusion Models via Adversarial Examplescited by 167
  9. 2021Dual Attention Suppression Attack: Generate Adversarial Camouflage in Physical Worldcited by 127
  10. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesiscited by 120
  11. 2023Mist: Towards Improved Adversarial Examples for Diffusion Modelscited by 94
  12. 2021Adversarial Sticker: A Stealthy Attack Method in the Physical Worldcited by 93
  13. 2019Universal Physical Camouflage Attacks on Object Detectorscited by 91
  14. 2022Physical Adversarial Attack meets Computer Vision: A Decade Surveycited by 67
  15. 2017Fast Feature Fool: A data independent approach to universal adversarial perturbationscited by 66
  16. 2023Toward effective protection against diffusion based mimicry through score distillationcited by 65
  17. 2018Adversarial Examples: Opportunities and Challengescited by 63
  18. 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 62
  19. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 57
  20. 2022Physical Attack on Monocular Depth Estimation with Optimal Adversarial Patchescited by 57
  21. 2020Transferable Perturbations of Deep Feature Distributionscited by 51
  22. 2020SLAP: Improving Physical Adversarial Examples with Short-Lived Adversarial Perturbationscited by 50
  23. 2021Adversarial Attacks for Tabular Data: Application to Fraud Detection and Imbalanced Datacited by 45
  24. 2023MetaCloak: Preventing Unauthorized Subject-driven Text-to-image Diffusion-based Synthesis via Meta-learningcited by 44
  25. 2023Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modelingcited by 41
  26. 2023Physically Adversarial Infrared Patches with Learnable Shapes and Locationscited by 39
  27. 2022Natural Color Fool: Towards Boosting Black-box Unrestricted Attackscited by 38
  28. 2023Can Protective Perturbation Safeguard Personal Data from Being Exploited by Stable Diffusion?cited by 38
  29. 2023Unlearnable Examples for Diffusion Models: Protect Data from Unauthorized Exploitationcited by 37
  30. 2023SimAC: A Simple Anti-Customization Method for Protecting Face Privacy against Text-to-Image Synthesis of Diffusion Modelscited by 36
  31. 2024A Survey of Recent Backdoor Attacks and Defenses in Large Language Modelscited by 36
  32. 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIcited by 35
  33. 2022Domain-invariant Feature Exploration for Domain Generalizationcited by 34
  34. 2023Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognitioncited by 33
  35. 2021Reliably fast adversarial training via latent adversarial perturbationcited by 29
  36. 2021Robust Feature-Level Adversaries are Interpretability Toolscited by 27
  37. 2019Harnessing the Vulnerability of Latent Layers in Adversarially Trained Modelscited by 26
  38. 2022Restricted Black-box Adversarial Attack Against DeepFake Face Swappingcited by 25

50 most cited of 106 All 106 (JSON)

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2025: 2; 2026: 2.

4 papers.

  1. 2025Explainable but Vulnerable: Adversarial Attacks on XAI Explanation in Cybersecurity Applicationscited by 1
  2. 2025On the Adversarial Robustness of Learning-based Conformal Novelty Detectioncited by 0
  3. 2026SRAW-Attack: Space-Reweighted Adversarial Warping Attack for SAR Target Recognitioncited by 0
  4. 2026Towards Universal Physical Adversarial Attacks via a Joint Multi-Objective and Multi-Model Optimization Frameworkcited by 0