logoalt Hacker News

slt202101/22/20254 repliesview on HN

you dont know what kind of backdoors are hidden in the model weights


Replies

LiamPowell01/22/2025

Can you elaborate on how any sort of backdoor could be hidden in the model weights?

It's a technical possibility to hide something in the code, but that would be a bit silly since there's not that much of it here. It's not technically possible to hide a backdoor in a set of numbers that are solely used as the operands to trivial mathematical operations, so I'm very curious about what sort of hidden backdoor you think is here.

show 1 reply
dkjaudyeqooe01/22/2025

I'm trying to think of what kind of adversarial 3D model the weights could produce. Perhaps a 3D goatse?

EMIRELADERO01/22/2025

I mean... you can just firewall it?

show 1 reply
suraci01/22/2025

Your concern is reasonable.

According to DOD, Tencent - which published this model - is a Chinese military company

https://www.bbc.com/news/articles/c9q78wn9g8zo