Generating Collisions on NeuralHash
Security and privacy
perceptual hash attacks
SHOW HN2021
22points
6comments
#1,321of 2,533 in 2021
Top 53%of 2021 by points
How HN took it
QuietFewer than 5 comments about the project
0 positive, 1 neutral or asking, 0 mixed, 1 critical, out of 2 comments about the project.
Docs: 0 for, 1 against
The thread, comment by comment
Each row is a top-level comment and its replies, in HN's order. Select a cell to open that comment on HN.
positive neutral or mixed critical about another commenter or something else the maker
What HN said
What people liked
Commenter says the hash-tolerance property explains why perceptual hashes are poor evidence
From 1 comment
What you're highlighting is the lack of avalanche effect with perceptual hashes (on purpose). This makes them great for identifying transformed content (e.g. local TV channels…
chaboud on HN
Objections
Title overstates the work since the maker lacks Apple's actual architecture and weights
From 1 comment
>I don't have the architecture nor the weights of the actual neural hash they use so this is only a POC in the general case. Then why is this titled "Generating Collisions on…
krapp on HN
Questions
How steganographic content would affect the perceptual hash similarity
From 1 comment
In the manual review failure case, you're saying that the reviewer would decrypt the steganographical encryption, discover the hidden offensive content, and thereby decide that…
tehnub on HN