Some links related to Apple’s NeuralHash algorithm, as it was reverse engineered and collisions can be generated so abuse with pictures matching sensitive hashes can be performed
Posted by jpluimers on 2021/08/24
Last week, I wrote [Archive.is] Jeroen Wiert Pluimers on Twitter: “Apple’s NeuralHash algorithm for automagically reporting sensitive images from iOS devices has not only been reverse engineered, but also collisions can now be generated. Now just wait for abuse of innocent pictures matching sensitive hashes. … “
Below, for my link archive, some relevant links on this:
- [Archive.is] stacksmashing on Twitter: “I generated a picture that shows its own NeuralHash… “
- [Wayback/Archive.is] anishathalye/neural-hash-collider: Preimage attack against NeuralHash 💣
- [Wayback/Archive.is] ImageNet contains naturally occurring NeuralHash collisions
NeuralHash is the perceptual hashing model that back’s Apple’s new CSAM (child sexual abuse material) reporting mechanism. It’s an algorithm that takes an image as input and returns a 96-bit unique identifier (a hash) that should match for two images that are “the same” (besides some minor perturbations like JPEG artifacts, resizing, or cropping).
- [Wayback/Archive.is] ImageNet contains naturally occurring NeuralHash collisions
- [Wayback/Archive.is] roboflow-ai/neuralhash-collisions: A catalog of naturally occurring images whose Apple NeuralHash is identical.
- Serious flaw in Apple’s CSAM scanner uncovered: [Wayback/Archive.is] Apple says collision in child-abuse hashing system is not a concern – The Verge
- [Wayback/Archive.is] AsuharietYgvar/AppleNeuralHash2ONNX: Convert Apple NeuralHash model for CSAM Detection to ONNX.
- [Wayback/Archive.is] Apple’s NeuralHash Algorithm Has Been Reverse-Engineered – Schneier on Security
- [Wayback/Archive.is] International Coalition Calls on Apple to Abandon Plan to Build Surveillance Capabilities into iPhones, iPads, and other Products – Center for Democracy and Technology
- [Wayback/Archive.is] iOS 15 – Wikipedia: CSAM Detection (NeuralHash)
- [Wayback/Archive.is] Hash collision in Apple NeuralHash model : programming
- Thread about duplicate hashes fore both related and unrelated images: [Wayback] Sarah Jamie Lewis on Twitter: “I let NeuralHash run most of the day in the background processing ~200K images. Didn’t find any absolute “random” hashes (a few were 2-3 bits close) – but did find a few sets like this – sets of burst photos which match All have the same hash: 75bbd25662074bdc7ac97677… “
- [Archive.is] Rich Harang on Twitter: “Do you see a difference between these two images? Apple’s NeuralHash thinks they differ on 52 of 96 bits (ed570844756690de887ceec3 vs 2d574044756690de887cfe43). No I won’t tell you how I did it, but it runs on CPU in about 10 seconds. NeuralHash is trivial to evade.… “
- [Archive.is] badidea 🪐 on Twitter: “neural hash c78fc26ec100f8508d4e60a3 🙂… “
–jeroen
The Wiert Corner - irregular stream of stuff 
Leave a Reply