mlsanityData to 7 Oct 2026

AdvFaces: Adversarial Face Synthesis

arXiv 1908.05008 ↗First posted 14 Aug 2019cs.CVcited by 59

Not on the map. Why?

Abstract (arXiv)

Face recognition systems have been shown to be vulnerable to adversarial examples resulting from adding small perturbations to probe images. Such adversarial images can lead state-of-the-art face recognition systems to falsely reject a genuine subject (obfuscation attack) or falsely match to an impostor (impersonation attack). Current approaches to crafting adversarial face images lack perceptual quality and take an unreasonable amount of time to generate them. We propose, AdvFaces, an automated adversarial face synthesis method that learns to generate minimal perturbations in the salient facial regions via Generative Adversarial Networks. Once AdvFaces is trained, it can automatically generate imperceptible perturbations that can evade state-of-the-art face matchers with attack success rates as high as 97.22% and 24.30% for obfuscation and impersonation attacks, respectively.

Key facts. Cited by 59 papers in the map (data through 7 Oct 2026). First posted on arXiv 14 Aug 2019.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 16; 2022: 9; 2023: 9; 2024: 15; 2025: 5; 2026: 5.

59 papers.

Sort:

By area:

  1. 2021Advances in adversarial attacks and defenses in computer vision: A surveycited by 127
  2. 2021Adv-Makeup: A New Imperceptible and Transferable Attack on Face Recognitioncited by 95
  3. 2023CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Imagescited by 84
  4. 2021Reverse Engineering of Generative Models: Inferring Model Hyperparameters from Generated Imagescited by 58
  5. 2023AdvDiff: Generating Unrestricted Adversarial Examples using Diffusion Modelscited by 46
  6. 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
  7. 2022Infrared Invisible Clothing:Hiding from Infrared Detectors at Multiple Angles in Real Worldcited by 42
  8. 2022Adv-Attribute: Inconspicuous and Transferable Adversarial Attack on Face Recognitioncited by 42
  9. 2021Biometrics: Trust, but Verifycited by 39
  10. 2023Sibling-Attack: Rethinking Transferable Adversarial Attacks against Face Recognitioncited by 32
  11. 2021Unified Detection of Digital and Physical Face Attackscited by 31
  12. 2021Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Modelcited by 19
38 more
  1. 2023Attacks in Adversarial Machine Learning: A Systematic Survey from the Life-cycle Perspectivecited by 19
  2. 2021Dodging Attack Using Carefully Crafted Natural Makeupcited by 17
  3. 2024Unified Physical-Digital Face Attack Detectioncited by 17
  4. 2021Adversarial Relighting Against Face Recognitioncited by 16
  5. 2021SoK: Anti-Facial Recognition Technologycited by 16
  6. 2021Generative Adversarial Networks: A Survey Towards Private and Secure Applicationscited by 15
  7. 2025Adv-CPG: A Customized Portrait Generation Framework with Facial Adversarial Attackscited by 13
  8. 2021Generative Adversarial Networks (GANs) in Networking: A Comprehensive Survey & Evaluationcited by 11
  9. 2022Discrete Point-wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognitioncited by 11
  10. 2024Personalized Privacy Protection Mask Against Unauthorized Facial Recognitioncited by 10
  11. 2021A Master Key Backdoor for Universal Impersonation Attack against DNN-based Face Verificationcited by 9
  12. 2024Face Reconstruction from Face Embeddings using Adapter to a Face Foundation Modelcited by 9
  13. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  14. 2022Similarity-based Gray-box Adversarial Attack Against Deep Face Recognitioncited by 8
  15. 2022RSTAM: An Effective Black-Box Impersonation Attack on Face Recognition using a Mobile and Compact Printercited by 7
  16. 2022Scale-free and Task-agnostic Attack: Generating Photo-realistic Adversarial Patterns with Patch Quilting Generatorcited by 5
  17. 2024Transferable Adversarial Face Attack with Text Controlled Attributecited by 5
  18. 2023AdvCloak: Customized Adversarial Cloak for Privacy Protectioncited by 4
  19. 2024ARoFace: Alignment Robustness to Improve Low-Quality Face Recognitioncited by 4
  20. 2024ID-Guard: A Universal Framework for Combating Facial Manipulation via Breaking Identificationcited by 4
  21. 2024A Survey on Physical Adversarial Attacks against Face Recognition Systemscited by 4
  22. 2024Beyond Spatial Explanations: Explainable Face Recognition in the Frequency Domaincited by 3
  23. 2024A Multi-task Adversarial Attack Against Face Authenticationcited by 3
  24. 2022GMFIM: A Generative Mask-guided Facial Image Manipulation Model for Privacy Preservationcited by 2
  25. 2024DIP-Watermark: A Double Identity Protection Method Based on Robust Adversarial Watermarkcited by 2
  26. 2024Non-Uniform Illumination Attack for Fooling Convolutional Neural Networkscited by 2
  27. 2025CryptoFace: End-to-End Encrypted Face Recognitioncited by 2
  28. 2021Robustness-via-Synthesis: Robust Training with Generative Adversarial Perturbationscited by 1
  29. 2021Adversarial Training for Face Recognition Systems using Contrastive Adversarial Learning and Triplet Loss Fine-tuningcited by 1
  30. 2023Semantic Adversarial Attacks on Face Recognition through Significant Attributescited by 1
  31. 2024Adversarial Identity Injection for Semantic Face Image Synthesiscited by 1
  32. 2024Boosting Unconstrained Face Recognition with Targeted Style Adversarycited by 1
  33. 2024ErasableMask: A Robust and Erasable Privacy Protection Scheme against Black-box Face Recognition Modelscited by 1
  34. 2025DArFace: Deformation Aware Robustness for Low Quality Face Recognitioncited by 1
  35. 2021Real-World Adversarial Examples involving Makeup Applicationcited by 0
  36. 2022Reliable Detection of Doppelg"angers based on Deep Face Representationscited by 0
  37. 2022Towards Assessing and Characterizing the Semantic Robustness of Face Recognitioncited by 0
  38. 2023AdvBiom: Adversarial Attacks on Biometric Matcherscited by 0

50 most cited of 59 All 59 (JSON)