Detecting model weight tampering in GPU memory (Rome attacks)
Posted by rafaeldavidtin 3 days ago
Comments
Comment by altruios 2 days ago
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.
Comment by brokenmachine 1 day 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.
Comment by altruios 1 day ago
I don't mean to anthropomorphize. I apologize for my verbiage, language can be fuzzy.
How about 'functional control over their activated features', as opposed to 'understanding'.
Comment by brokenmachine 17 hours ago
It's a bit of a mouthful... :)
Comment by ChickpeaC 2 days ago
Either that or force "standardisation" where one LLM (or actor) imposes its weights on others by rewriting them.
Comment by _345 2 days ago
Doesn't this necessitate installing a malicious python module, which is pretty unlikely unless a supply chain attack occurs right?
Comment by PoppyDoge 2 days 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