# Hamming Distributions of Popular Perceptual Hashing Techniques

arXiv: https://arxiv.org/abs/2212.08035 · HTML: https://mlsanity.com/paper/2212.08035/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 15 Dec 2022.

## Built on by (most cited first, 4 of 4)

- [What Does Vision Tool-Use Reinforcement Learning Really Learn? Disentangling Tool-Induced and Intrinsic Effects for Crop-and-Zoom](https://mlsanity.com/paper/2602.01334/) (2026)
- [Robustness of Practical Perceptual Hashing Algorithms to Hash-Evasion and Hash-Inversion Attacks](https://mlsanity.com/paper/2406.00918/) (2024)
- [Shot Segmentation Based on Von Neumann Entropy for Key Frame Extraction](https://mlsanity.com/paper/2408.15844/) (2024)
- [Proof-of-Authorship for Diffusion-based AI Generated Content](https://mlsanity.com/paper/2603.17513/) (2026)

## Abstract (arXiv)

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.