mlsanityData to 7 Oct 2026

LowKey: Leveraging Adversarial Attacks to Protect Social Media Users from Facial Recognition

arXiv 2101.07922 ↗First posted 20 Jan 2021cs.CV cs.CR cs.LGcited by 92

Not on the map. Why?

Abstract (arXiv)

Facial recognition systems are increasingly deployed by private corporations, government agencies, and contractors for consumer services and mass surveillance programs alike. These systems are typically built by scraping social media profiles for user images. Adversarial perturbations have been proposed for bypassing facial recognition systems. However, existing methods fail on full-scale systems and commercial APIs. We develop our own adversarial filter that accounts for the entire image processing pipeline and is demonstrably effective against industrial-grade pipelines that include face detection and large scale databases. Additionally, we release an easy-to-use webtool that significantly degrades the accuracy of Amazon Rekognition and the Microsoft Azure Face Recognition API, reducing the accuracy of each to below 1%.

Key facts. Cited by 92 papers in the map (data through 7 Oct 2026). Builds on 18 of its 32 references that are in the map. First posted on arXiv 20 Jan 2021.

Builds on

18 of 32 references.

References · 18

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  3. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  4. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  5. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  6. 2016Adversarial examples in the physical worldcited by 1,762
  7. 2018CosFace: Large Margin Cosine Loss for Deep Face Recognitioncited by 968
  8. 2017SphereFace: Deep Hypersphere Embedding for Face Recognitioncited by 733
  9. 2016MS-Celeb-1M: A Dataset and Benchmark for Large-Scale Face Recognitioncited by 621
  10. 2015The MegaFace Benchmark: 1 Million Faces for Recognition at Scalecited by 199
  11. 2019Making an Invisibility Cloak: Real World Adversarial Attacks on Object Detectorscited by 155
  12. 2020Perceptual Adversarial Robustness: Defense Against Unseen Threat Modelscited by 137
6 more
  1. 2020Towards Transferable Adversarial Attack against Deep Face Recognitioncited by 79
  2. 2016UMDFaces: An Annotated Face Dataset for Training Deep Networkscited by 42
  3. 2019Adversarial attacks on Copyright Detection Systemscited by 11
  4. 2020Adversarial Attacks on Machine Learning Systems for High-Frequency Tradingcited by 11
  5. 2019WITCHcraft: Efficient PGD attacks with random step sizecited by 4
  6. 2020A Method for Curation of Web-Scraped Face Image Datasetscited by 3

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2021: 14; 2022: 11; 2023: 31; 2024: 15; 2025: 8; 2026: 13.

92 papers.

Sort:

By area:

  1. 2023Glaze: Protecting Artists from Style Mimicry by Text-to-Image Modelscited by 200
  2. 2021Adversarial Examples Make Strong Poisonscited by 115
  3. 2023Anti-DreamBooth: Protecting users from personalized text-to-image synthesiscited by 114
  4. 2022Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-robust Makeup Transfercited by 77
  5. 2023Nightshade: Prompt-Specific Poisoning Attacks on Text-to-Image Generative Modelscited by 72
  6. 2021Availability Attacks Create Shortcutscited by 60
  7. 2021Better Safe Than Sorry: Preventing Delusive Adversaries with Adversarial Trainingcited by 58
  8. 2021Data Poisoning Won't Save You From Facial Recognitioncited by 45
  9. 2023CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Searchcited by 42
  10. 2023Image Shortcut Squeezing: Countering Perturbative Availability Poisons with Compressioncited by 39
  11. 2021Preventing Unauthorized Use of Proprietary Data: Poisoning for Secure Dataset Releasecited by 35
  12. 2022Unlearnable Clusters: Towards Label-agnostic Unlearnable Examplescited by 35
38 more
  1. 2023DiffProtect: Generate Adversarial Examples with Diffusion Models for Facial Privacy Protectioncited by 34
  2. 2022Indiscriminate Poisoning Attacks on Unsupervised Contrastive Learningcited by 32
  3. 2023IMPRESS: Evaluating the Resilience of Imperceptible Perturbations Against Unauthorized Data Usage in Diffusion-Based Generative AIcited by 32
  4. 2024DiffAM: Diffusion-based Adversarial Makeup Transfer for Facial Privacy Protectioncited by 31
  5. 2023Algorithmic Collective Action in Machine Learningcited by 30
  6. 2022Rethinking Bias Mitigation: Fairer Architectures Make for Fairer Face Recognitioncited by 26
  7. 2022OPOM: Customized Invisible Cloak towards Face Privacy Protectioncited by 22
  8. 2023Generative Watermarking Against Unauthorized Subject-Driven Image Synthesiscited by 21
  9. 2021Technical Challenges for Training Fair Neural Networkscited by 20
  10. 2023Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attackscited by 18
  11. 2021SoK: Anti-Facial Recognition Technologycited by 16
  12. 2023The Best Defense is a Good Offense: Adversarial Augmentation against Adversarial Attackscited by 15
  13. 2024Geometry Cloak: Preventing TGS-based 3D Reconstruction from Copyrighted Imagescited by 15
  14. 2024Prompt-Agnostic Adversarial Perturbation for Customized Diffusion Modelscited by 14
  15. 2023Detection and Defense of Unlearnable Examplescited by 13
  16. 2021Am I a Real or Fake Celebrity? Measuring Commercial Face Recognition Web APIs under Deepfake Impersonation Attackcited by 12
  17. 2021Robustness Disparities in Commercial Face Detectioncited by 11
  18. 2024Talking Nonsense: Probing Large Language Models' Understanding of Adversarial Gibberish Inputscited by 11
  19. 2024Personalized Privacy Protection Mask Against Unauthorized Facial Recognitioncited by 10
  20. 2021Fairness Properties of Face Recognition and Obfuscation Systemscited by 9
  21. 2023Towards Prompt-robust Face Privacy Protection via Adversarial Decoupling Augmentation Frameworkcited by 9
  22. 2024Dormant: Defending against Pose-driven Human Image Animationcited by 9
  23. 2023Toward Face Biometric De-identification using Adversarial Examplescited by 8
  24. 2021Rethinking Image-Scaling Attacks: The Interplay Between Vulnerabilities in Machine Learning Systemscited by 7
  25. 2023Face Recognition in the age of CLIP & Billion image datasetscited by 7
  26. 2024Rethinking Impersonation and Dodging Attacks on Face Recognition Systemscited by 7
  27. 2024Makeup-Guided Facial Privacy Protection via Untrained Neural Network Priorscited by 7
  28. 2023Can Pretrained Language Models Derive Correct Semantics from Corrupt Subwords under Noise?cited by 6
  29. 2023Face Encryption via Frequency-Restricted Identity-Agnostic Attackscited by 6
  30. 2023Segue: Side-information Guided Generative Unlearnable Examples for Facial Privacy Protection in Real Worldcited by 6
  31. 2022Robustness Disparities in Face Detectioncited by 5
  32. 20233D-Aware Adversarial Makeup Generation for Facial Privacy Protectioncited by 5
  33. 2023Improving Visual Quality and Transferability of Adversarial Attacks on Face Recognition Simultaneously with Adversarial Restorationcited by 5
  34. 2023My Art My Choice: Adversarial Protection Against Unruly AIcited by 5
  35. 2023Adversarial Machine Learning for Social Good: Reframing the Adversary as an Allycited by 5
  36. 2025BlurGuard: A Simple Approach for Robustifying Image Protection Against AI-Powered Editingcited by 5
  37. 2021Identification of Attack-Specific Signatures in Adversarial Examplescited by 4
  38. 2021Preemptive Image Robustification for Protecting Users against Man-in-the-Middle Adversarial Attackscited by 4

50 most cited of 92 All 92 (JSON)