HackerReposA FIELD GUIDE TO OPEN SOURCE
ProSponsor the shelf♧ 0
← Back to top all-time
roboflow
neuralhash-collisions
JavaScript2021–2021
roboflow / neuralhash-collisions

neuralhash-collisions

A catalog of naturally occurring images whose Apple NeuralHash is identical.

3Distinct people
3Mentions
0Explicit recommenders
150GitHub stars
REPOSITORY AT A GLANCE

What to know before exploring

What it is

A catalog of naturally occurring images whose Apple NeuralHash is identical.

GitHub

Where it is used

No documented product use has been verified yet.

What people are saying

No recommendation phrase was found in the indexed comments.

No classified warning is attached to this page. Read the discussions before treating silence as approval.

Also in these discussions

No other repository is repeatedly linked in the same discussions.

This week on Hacker News

Nov 8–Nov 15 UTC · Direct repository links and separately labeled related project stories. Indexed through 11/15/2026, 10:01:16 PM UTC.

No direct repository links were found in the indexed HN discussions over the past seven days. Older discussions are available below.

Mentions over time

HN mentions by week3 dated mentions

Observed mentions: 2021-08-19 17:56:26 UTC to 2021-09-23 09:02:15 UTC. Weeks start Monday, UTC.

012021-08-16 00:00:00 UTC to 2021-08-23 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsAug 162021-08-23 00:00:00 UTC to 2021-08-30 00:00:00 UTC (exclusive): 1 mentions; 1 submissions, 0 comments2021-08-30 00:00:00 UTC to 2021-09-06 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 commentsAug 302021-09-06 00:00:00 UTC to 2021-09-13 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-09-13 00:00:00 UTC to 2021-09-20 00:00:00 UTC (exclusive): 0 mentions; 0 submissions, 0 comments2021-09-20 00:00:00 UTC to 2021-09-27 00:00:00 UTC (exclusive): 1 mentions; 0 submissions, 1 commentsSep 20

Counts come from the repository’s dated source evidence. Index cutoff: 2026-11-02 08:16:59 UTC.

View mention counts and date ranges
UTC ranges include their start and exclude their end. Select a period to filter the source evidence.
PeriodStart (UTC)End (exclusive, UTC)MentionsSubmissionsComments
Aug 162021-08-16 00:00:00 UTC2021-08-23 00:00:00 UTC101
Aug 232021-08-23 00:00:00 UTC2021-08-30 00:00:00 UTC110
Aug 302021-08-30 00:00:00 UTC2021-09-06 00:00:00 UTC000
Sep 62021-09-06 00:00:00 UTC2021-09-13 00:00:00 UTC000
Sep 132021-09-13 00:00:00 UTC2021-09-20 00:00:00 UTC000
Sep 202021-09-20 00:00:00 UTC2021-09-27 00:00:00 UTC101

What Hacker News says

1 sources
Reminder that it's perceptual hashes, not cryptographic hashes. So it's enough that images have enough visual resemblance, according to the model. Natural collisions have been observed and generating collisions for planting on someone elses device is trivial. Apple also only recieves a DB of hashes and so have no way to verify that they're only scanning for CSAM and not other "undesirable" content. https://github.com/roboflow-ai/neuralhash-collisions https://github.com/anishathalye/neural-hash-collider
In Google Drive of historical footage locked and flagged as terrorist activity

MAKE YOURSELF AT HOME

A few shortcuts

/
Search the collection
?
Open this guide
Esc
Close dialogs and navigation

Your saved repositories and interests stay in this browser.