mlsanityData to 7 Oct 2026

Toward Face Biometric De-identification using Adversarial Examples

arXiv 2302.03657 ↗First posted 7 Feb 2023cs.CV cs.CR cs.LGcited by 8

Not on the map. Why?

Abstract (arXiv)

The remarkable success of face recognition (FR) has endangered the privacy of internet users particularly in social media. Recently, researchers turned to use adversarial examples as a countermeasure. In this paper, we assess the effectiveness of using two widely known adversarial methods (BIM and ILLC) for de-identifying personal images. We discovered, unlike previous claims in the literature, that it is not easy to get a high protection success rate (suppressing identification rate) with imperceptible adversarial perturbation to the human visual system. Finally, we found out that the transferability of adversarial examples is highly affected by the training parameters of the network with which they are generated.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 22 of its 38 references that are in the map. First posted on arXiv 7 Feb 2023.

Builds on

22 of 38 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. 2017Squeeze-and-Excitation Networkscited by 4,763
  5. 2015FaceNet: A Unified Embedding for Face Recognition and Clusteringcited by 2,833
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  8. 2017VGGFace2: A dataset for recognising faces across pose and agecited by 911
  9. 2016Joint Face Detection and Alignment using Multi-task Cascaded Convolutional Networkscited by 895
  10. 2017Evasion Attacks against Machine Learning at Test Timecited by 686
  11. 2021LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognitioncited by 92
  12. 2020Face Image Quality Assessment: A Literature Surveycited by 79
10 more
  1. 2020SensitiveLoss: Improving Accuracy and Fairness of Face Representations with Discrimination-Aware Deep Learningcited by 50
  2. 2020Biometric Quality: Review and Application to Face Recognition with FaceQnetcited by 41
  3. 2022OPOM: Customized Invisible Cloak towards Face Privacy Protectioncited by 22
  4. 2022Facial Soft Biometrics for Recognition in the Wild: Recent Works, Annotation, and COTS Evaluationcited by 19
  5. 2019SensitiveNets: Learning Agnostic Representations with Application to Face Imagescited by 17
  6. 2021Quality Measures in Biometric Systemscited by 12
  7. 2020Ulixes: Facial Recognition Privacy with Adversarial Machine Learningcited by 7
  8. 2021OTB-morph: One-Time Biometrics via Morphing applied to Face Templatescited by 4
  9. 2020Learning Emotional-Blinded Face Representationscited by 3
  10. 2021Introduction to Presentation Attack Detection in Iris Biometrics and Recent Advancescited by 3

Built on by

Cited by year

Citing papers per year: 2023: 3; 2024: 2; 2025: 3.

8 papers.

  1. 2024Is My Data in Your AI? Membership Inference Test (MINT) applied to Face Biometricscited by 12
  2. 2025PBa-LLM: Privacy- and Bias-aware NLP using Named-Entity Recognition (NER)cited by 10
  3. 2024Face De-identification: State-of-the-art Methods and Comparative Studiescited by 9
  4. 2023SaFL: Sybil-aware Federated Learning with Application to Face Recognitioncited by 2
  5. 2023Blockchain and Biometrics: Survey, GDPR Analysis, and Future Directionscited by 1
  6. 2023PAD-Phys: Exploiting Physiology for Presentation Attack Detection in Face Biometricscited by 1
  7. 2025Palmprint De-Identification Using Diffusion Model for High-Quality and Diverse Synthesiscited by 0
  8. 2025NLML-HPE: Head Pose Estimation with Limited Data via Manifold Learningcited by 0