mlsanityData to 14 Oct 2026

Re-purposing Perceptual Hashing based Client Side Scanning for Physical Surveillance

arXiv 2212.04107 ↗First posted 8 Dec 2022cs.CR cs.CVcited by 0

Not on the map. Why?

Abstract (arXiv)

Content scanning systems employ perceptual hashing algorithms to scan user content for illegal material, such as child pornography or terrorist recruitment flyers. Perceptual hashing algorithms help determine whether two images are visually similar while preserving the privacy of the input images. Several efforts from industry and academia propose to conduct content scanning on client devices such as smartphones due to the impending roll out of end-to-end encryption that will make server-side content scanning difficult. However, these proposals have met with strong criticism because of the potential for the technology to be misused and re-purposed. Our work informs this conversation by experimentally characterizing the potential for one type of misuse -- attackers manipulating the content scanning system to perform physical surveillance on target locations. Our contributions are threefold: (1) we offer a definition of physical surveillance in the context of client-side image scanning systems; (2) we experimentally characterize this risk and create a surveillance algorithm that achieves physical surveillance rates of >40% by poisoning 5% of the perceptual hash database; (3) we experimentally study the trade-off between the robustness of client-side image scanning systems and surveillance, showing that more robust detection of illegal material leads to increased potential for physical surveillance.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 19 of its 37 references that are in the map. First posted on arXiv 8 Dec 2022.

Builds on

19 of 37 references.

References · 19

  1. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
  2. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,451
  3. 2018Black-box Adversarial Attacks with Limited Queries and Informationcited by 501
  4. 2022Diffusion Models for Adversarial Purificationcited by 476
  5. 2018Certified Robustness to Adversarial Examples with Differential Privacycited by 468
  6. 2018Certified Defenses against Adversarial Examplescited by 306
  7. 2021DICE: Leveraging Sparsification for Out-of-Distribution Detectioncited by 166
  8. 2022Is Out-of-Distribution Detection Learnable?cited by 109
  9. 2020From ImageNet to Image Classification: Contextualizing Progress on Benchmarkscited by 90
  10. 2017Robust Physical-World Attacks on Deep Learning Modelscited by 72
  11. 2021Learning to Break Deep Perceptual Hashing: The Use Case NeuralHashcited by 25
  12. 2022Out-of-distribution Detection via Frequency-regularized Generative Modelscited by 23
7 more
  1. 2022On the Limitations of Stochastic Pre-processing Defensescited by 21
  2. 2021SoK: Anti-Facial Recognition Technologycited by 16
  3. 2021Adversarial Detection Avoidance Attacks: Evaluating the robustness of perceptual hashing-based client-side scanningcited by 7
  4. 2021Bugs in our Pockets: The Risks of Client-Side Scanningcited by 6
  5. 2018Learning to Learn from Web Data through Deep Semantic Embeddingscited by 5
  6. 2020Adversarial collision attacks on image hashing functionscited by 5
  7. 2019PDQ & TMK + PDQF -- A Test Drive of Facebook's Perceptual Hashing Algorithmscited by 4

Built on by

Not cited yet.