mlsanityData to 7 Oct 2026

Towards Assessing and Characterizing the Semantic Robustness of Face Recognition

arXiv 2202.04978 ↗First posted 10 Feb 2022cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Deep Neural Networks (DNNs) lack robustness against imperceptible perturbations to their input. Face Recognition Models (FRMs) based on DNNs inherit this vulnerability. We propose a methodology for assessing and characterizing the robustness of FRMs against semantic perturbations to their input. Our methodology causes FRMs to malfunction by designing adversarial attacks that search for identity-preserving modifications to faces. In particular, given a face, our attacks find identity-preserving variants of the face such that an FRM fails to recognize the images belonging to the same identity. We model these identity-preserving semantic modifications via direction- and magnitude-constrained perturbations in the latent space of StyleGAN. We further propose to characterize the semantic robustness of an FRM by statistically describing the perturbations that induce the FRM to malfunction. Finally, we combine our methodology with a certification technique, thus providing (i) theoretical guarantees on the performance of an FRM, and (ii) a formal description of how an FRM may model the notion of face identity.

Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 50 of its 62 references that are in the map. First posted on arXiv 10 Feb 2022.

Builds on

50 of 62 references.

References · 50

  1. 2019PyTorch: An Imperative Style, High-Performance Deep Learning Librarycited by 20,160
  2. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  3. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  4. 2018A Style-Based Generator Architecture for Generative Adversarial Networkscited by 5,986
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2013Efficient Estimation of Word Representations in Vector Spacecited by 4,346
  7. 2015Delving Deep into Rectifiers: Surpassing Human-Level Performance on ImageNet Classificationcited by 3,590
  8. 2019Analyzing and Improving the Image Quality of StyleGANcited by 3,580
  9. 2013Playing Atari with Deep Reinforcement Learningcited by 3,211
  10. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  11. 2017Progressive Growing of GANs for Improved Quality, Stability, and Variationcited by 2,967
  12. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
38 more
  1. 2018Large Scale GAN Training for High Fidelity Natural Image Synthesiscited by 2,609
  2. 2020Shortcut Learning in Deep Neural Networkscited by 1,928
  3. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  4. 2018ImageNet-trained CNNs are biased towards texture; increasing shape bias improves accuracy and robustnesscited by 1,430
  5. 2019Certified Adversarial Robustness via Randomized Smoothingcited by 1,324
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2018Obfuscated Gradients Give a False Sense of Security: Circumventing Defenses to Adversarial Examplescited by 1,259
  8. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  9. 2020Fast is better than free: Revisiting adversarial trainingcited by 723
  10. 2019Interpreting the Latent Space of GANs for Semantic Face Editingcited by 691
  11. 2020GANSpace: Discovering Interpretable GAN Controlscited by 612
  12. 2017Provable defenses against adversarial examples via the convex outer adversarial polytopecited by 564
  13. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 462
  14. 2014Learning Face Representation from Scratchcited by 451
  15. 2019On Evaluating Adversarial Robustnesscited by 442
  16. 2020Closed-Form Factorization of Latent Semantics in GANscited by 407
  17. 2020InterFaceGAN: Interpreting the Disentangled Face Representation Learned by GANscited by 393
  18. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  19. 2020Unsupervised Discovery of Interpretable Directions in the GAN Latent Spacecited by 288
  20. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  21. 2018Constructing Unrestricted Adversarial Examples with Generative Modelscited by 135
  22. 2017Fader Networks: Manipulating Images by Sliding Attributescited by 118
  23. 2020MACER: Attack-free and Scalable Robust Training via Maximizing Certified Radiuscited by 114
  24. 2019Semantic Hierarchy Emerges in Deep Generative Representations for Scene Synthesiscited by 106
  25. 2019SemanticAdv: Generating Adversarial Examples via Attribute-conditional Image Editingcited by 93
  26. 2019Unrestricted Adversarial Examples via Semantic Manipulationcited by 84
  27. 2017A General Framework for Adversarial Examples with Objectivescited by 82
  28. 2019AdvFaces: Adversarial Face Synthesiscited by 59
  29. 2019Semantic Adversarial Attacks: Parametric Transformations That Fool Deep Classifierscited by 56
  30. 2021WarpedGANSpace: Finding non-linear RBF paths in GAN latent spacecited by 48
  31. 2018Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Networkcited by 38
  32. 2018Unravelling Robustness of Deep Learning based Face Recognition Against Adversarial Attackscited by 31
  33. 2021Exploring Adversarial Fake Images on Face Manifoldcited by 24
  34. 2021ANCER: Anisotropic Certification via Sample-wise Volume Maximizationcited by 23
  35. 2018Fast Geometrically-Perturbed Adversarial Facescited by 22
  36. 2021DeformRS: Certifying Input Deformations with Randomized Smoothingcited by 17
  37. 2019Adversarial Image Translation: Unrestricted Adversarial Examples in Face Recognition Systemscited by 12
  38. 2021Simulated Adversarial Testing of Face Recognition Modelscited by 10

Built on by

Not cited yet.