English

Perceptual Hash Inversion Attacks on Image-Based Sexual Abuse Removal Tools

Cryptography and Security 2024-12-10 v1

Abstract

We show that perceptual hashing, crucial for detecting and removing image-based sexual abuse (IBSA) online, faces vulnerabilities from low-budget inversion attacks based on generative AI. This jeopardizes the privacy of users, especially vulnerable groups. We advocate to implement secure hash matching in IBSA removal tools to mitigate potentially fatal consequences.

Cite

@article{arxiv.2412.06056,
  title  = {Perceptual Hash Inversion Attacks on Image-Based Sexual Abuse Removal Tools},
  author = {Sophie Hawkes and Christian Weinert and Teresa Almeida and Maryam Mehrnezhad},
  journal= {arXiv preprint arXiv:2412.06056},
  year   = {2024}
}

Comments

Original Publication: IEEE Security & Privacy Magazine 2024

R2 v1 2026-06-28T20:27:11.886Z