mlsanityData to 7 Oct 2026

Universal Adversarial Spoofing Attacks against Face Recognition

arXiv 2110.00708 ↗First posted 2 Oct 2021cs.CV cs.CR cs.LGcited by 4

Not on the map. Why?

Abstract (arXiv)

We assess the vulnerabilities of deep face recognition systems for images that falsify/spoof multiple identities simultaneously. We demonstrate that, by manipulating the deep feature representation extracted from a face image via imperceptibly small perturbations added at the pixel level using our proposed Universal Adversarial Spoofing Examples (UAXs), one can fool a face verification system into recognizing that the face image belongs to multiple different identities with a high success rate. One characteristic of the UAXs crafted with our method is that they are universal (identity-agnostic); they are successful even against identities not known in advance. For a certain deep neural network, we show that we are able to spoof almost all tested identities (99%), including those not known beforehand (not included in training). Our results indicate that a multiple-identity attack is a real threat and should be taken into account when deploying face recognition systems.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 22 of its 31 references that are in the map. First posted on arXiv 2 Oct 2021.

Builds on

22 of 31 references.

References · 22

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2013Intriguing properties of neural networkscited by 5,114
  6. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  7. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  8. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  9. 2016Adversarial Machine Learning at Scalecited by 934
  10. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  11. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  12. 2016Universal adversarial perturbationscited by 774
10 more
  1. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  2. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  3. 2014Learning Face Representation from Scratchcited by 451
  4. 2019Efficient Decision-based Black-box Adversarial Attacks on Face Recognitioncited by 173
  5. 2014Deep Learning Face Representation by Joint Identification-Verificationcited by 162
  6. 2018Attacks on State-of-the-Art Face Recognition using Attentional Adversarial Attack Generative Networkcited by 38
  7. 2017Toward Open-Set Face Recognitioncited by 29
  8. 2016LOTS about Attacking Deep Featurescited by 14
  9. 2020Generating Master Faces for Use in Performing Wolf Attacks on Face Recognition Systemscited by 13
  10. 2019Multiple-Identity Image Attacks Against Face-based Identity Verificationcited by 2

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 1; 2022: 0; 2023: 1; 2024: 0; 2025: 1; 2026: 1.

4 papers.

  1. 2021Adversarial Mask: Real-World Universal Adversarial Attack on Face Recognition Modelcited by 19
  2. 2025Democratic Training Against Universal Adversarial Perturbationscited by 1
  3. 2023Generalized Attacks on Face Verification Systemscited by 0
  4. 2026Face De-Identification: A Domain-Centric Survey from Capture to Processingcited by 0