AsuharietYgvar/AppleNeuralHash2ONNX

Convert Apple NeuralHash model for CSAM Detection to ONNX.

45
/ 100
Emerging

This project allows you to convert Apple's NeuralHash model into a standard ONNX format. This means you can take the specific image recognition logic used by Apple for content detection and use it independently. You provide the original Apple NeuralHash model files and image files, and it generates a unique 96-bit binary hash for each image. This is primarily useful for digital forensics experts, content moderation platform developers, or researchers studying perceptual hashing.

1,536 stars. No commits in the last 6 months.

Use this if you need to generate perceptual hashes for images using Apple's NeuralHash algorithm outside of Apple's ecosystem, for example, to test images against known hashes for content verification.

Not ideal if you are looking for a general-purpose image hashing library or a tool that doesn't require extracting proprietary model files from Apple devices or software.

digital-forensics content-moderation image-analysis perceptual-hashing child-safety-tech
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 10 / 25
Maturity 16 / 25
Community 19 / 25

How are scores calculated?

Stars

1,536

Forks

127

Language

Python

License

Apache-2.0

Last pushed

Aug 21, 2021

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/AsuharietYgvar/AppleNeuralHash2ONNX"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.