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

TL;DR

This paper reveals vulnerabilities in perceptual hashing used for detecting and removing IBSA online, demonstrating how generative AI can invert hashes and compromise user privacy, urging for more secure hash matching methods.

Contribution

It introduces the concept of low-budget generative AI inversion attacks on perceptual hashes in IBSA removal tools, highlighting a critical security flaw.

Findings

Perceptual hashes can be inverted using generative AI techniques.

Vulnerabilities threaten user privacy, especially for vulnerable groups.

Secure hash matching is recommended to mitigate risks.

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.