login

Rendered at 12:03:31 GMT+0000 (Coordinated Universal Time) with Rails + React on Rails RSC.

Detecting model weight tampering in GPU memory (Rome attacks) (stealthium.io)

28 points by rafaeldavidtin 1d ago | 5 comments

Curious.

This feels like a tool to add to an LLM, being able to modify it's own weights, to be able to relearn, refine its own understanding.

brokenmachine 11h ago

Not to jump on you, but it just irritates me when people anthropomorphize LLMs...

LLMs don't "understand".

Don't fall for the marketing and overstate their ability.

ChickpeaC 23h ago

Either that or force "standardisation" where one LLM (or actor) imposes its weights on others by rewriting them.

_345 1d ago

Doesn't this necessitate installing a malicious python module, which is pretty unlikely unless a supply chain attack occurs right?

PoppyDoge 23h ago

Yes - the start of this attack would most likely be a supply chain attack. Good thing we haven't seen many PyPI attacks this year hey? Imagine if the LiteLLM attack had something like this inside of it versus the more noticeable credential stealer the bad versions then had