Squint Hard Enough: Attacking Perceptual Hashing with Adversarial Machine Learning

Jonathan Prokos, Neil Fendley, Matthew Green, Roei Schuster, Eran Tromer, Tushar M. Jois, Yinzhi Cao

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

Abstract

Many online communications systems use perceptual hash matching systems to detect illicit files in user content. These systems employ specialized perceptual hash functions such as Microsoft’s PhotoDNA or Facebook’s PDQ to produce a compact digest of an image file that can be approximately compared to a database of known illicit-content digests. Recently, several proposals have suggested that hash-based matching systems be incorporated into client-side and end-to-end encrypted (E2EE) systems: in these designs, files that register as illicit content will be reported to the provider, while the remaining content will be sent confidentially. By using perceptual hashing to determine confidentiality guarantees, this new setting significantly changes the function of existing perceptual hashing – thus motivating the need to evaluate these functions from an adversarial perspective, using their perceptual capabilities against them. For example, an attacker may attempt to trigger a match on innocuous, but politically-charged, content in an attempt to stifle speech. In this work we develop threat models for perceptual hashing algorithms in an adversarial setting, and present attacks against the two most widely deployed algorithms: PhotoDNA and PDQ. Our results show that it is possible to efficiently generate targeted second-preimage attacks in which an attacker creates a variant of some source image that matches some target digest. As a complement to this main result, we also further investigate the production of images that facilitate detection avoidance attacks, continuing a recent investigation of Jain et al. Our work shows that existing perceptual hash functions are likely insufficiently robust to survive attacks on this new setting.

Original languageEnglish
Title of host publication32nd USENIX Security Symposium, USENIX Security 2023
PublisherUSENIX Association
Pages211-228
Number of pages18
ISBN (Electronic)9781713879497
StatePublished - 2023
Event32nd USENIX Security Symposium, USENIX Security 2023 - Anaheim, United States
Duration: 9 Aug 202311 Aug 2023

Publication series

Name32nd USENIX Security Symposium, USENIX Security 2023
Volume1

Conference

Conference32nd USENIX Security Symposium, USENIX Security 2023
Country/TerritoryUnited States
CityAnaheim
Period9/08/2311/08/23

Funding

FundersFunder number
National Science FoundationCNS-1653110, CNS-1854000, CNS-1801479, CNS-1955172
Office of Naval ResearchN00014-19-1-2292
Defense Advanced Research Projects AgencyHR001120C0084
JPMorgan Chase and Company
Google

    Fingerprint

    Dive into the research topics of 'Squint Hard Enough: Attacking Perceptual Hashing with Adversarial Machine Learning'. Together they form a unique fingerprint.

    Cite this