Explore a 15-minute conference talk from USENIX Security '23 that delves into the vulnerabilities of perceptual hashing algorithms used in online content moderation systems. Learn about the potential risks of incorporating these hash-based matching systems into client-side and end-to-end encrypted (E2EE) communications. Discover how researchers developed threat models and attacks against widely deployed algorithms like PhotoDNA and PDQ, demonstrating the possibility of generating targeted second-preimage attacks and detection avoidance techniques. Gain insights into the implications of these findings for the robustness of existing perceptual hash functions in adversarial settings, particularly in the context of determining confidentiality guarantees for user content.
Squint Hard Enough - Attacking Perceptual Hashing with Adversarial Machine Learning
Overview
Syllabus
USENIX Security '23 - Squint Hard Enough: Attacking Perceptual Hashing with Adversarial Machine...
Taught by
USENIX
Related Courses
-
A Beginner's Guide to Adversarial Machine Learning
-
Adversarial Examples in Machine Learning - Crafting and Defending Against Attacks
-
Lotto: Secure Participant Selection against Adversarial Servers in Federated Learning
-
Attacking Machine Learning - On the Security and Privacy of Neural Networks
-
Building Realistic Machine Learning Systems for Security
-
Vulnerability of Machine Learning Algorithms to Adversarial Attacks for Cyber-Physical Power Systems
