Hamming Distributions of Popular Perceptual Hashing Techniques

McKeown, Sean; Buchanan, William J.

Abstract

Content-based file matching has been widely deployed for decades, largely for the detection of sources of copyright infringement, extremist materials, and abusive sexual media. Perceptual hashes, such as Microsoft's PhotoDNA, are one automated mechanism for facilitating detection, allowing for machines to approximately match visual features of an image or video in a robust manner. However, there does not appear to be much public evaluation of such approaches, particularly when it comes to how effective they are against content-preserving modifications to media files. In this paper we present a million-image scale evaluation of several perceptual hashing archetypes for popular algorithms (including Facebook's PDQ, Apple's Neuralhash, and the popular pHash library) against seven image variants. The focal point is the distribution of Hamming distance scores between both unrelated images and image variants to better understand the problems faced by each approach.

• Journal Article Type: Article
• Conference Name: DFRWS EU 2023
• Acceptance Date: Nov 28, 2022
• Online Publication Date: Mar 20, 2023
• Publication Date: 2023-03
• Deposit Date: Jan 9, 2023
• Publicly Available Date: Mar 20, 2023
• Journal: Forensic Science International: Digital Investigation
• Electronic ISSN: 2666-2817
• Publisher: Elsevier
• Peer Reviewed: Peer Reviewed
• Volume: 44
• Issue: Supplement
• Article Number: 301509
• DOI: https://doi.org/10.1016/j.fsidi.2023.301509
• Keywords: Perceptual Hashing; Fuzzy Hashing; Hash Matching; CSAM; Image Forensics
• Public URL: http://researchrepository.napier.ac.uk/Output/3000437
• Publisher URL: https://www.sciencedirect.com/journal/forensic-science-international-digital-investigation/