Comment by rao-v
5 hours ago
Ask the least smart LLM you have access to (I tried gemini lite flash) to make a list of ways for processes in microVMs to use a sidechannel attack to talk to each other and you'll get quite a list (including obviously cache hits/misses). Heck a smart CS junior would come up with it. It's well studied!
> Ask the least smart LLM
> Heck a smart CS junior would come up with it.
That’s somewhat worrisome.
LLM can recite it because it's in the training data (or Google it). CS Junior could invent it independently.
I'd like to see an LLM-aided implementation of row hammer being used for something like this.
this is just for common designs..you can design much better than common designs if you free your mind from old OS dev thinking if you read all the manuals yourself.
AI wont help u there :-). they will tell u how to build what others already did, which obviously is not good enough
I don't think that's the full picture. If you include these manuals as reference for a strong model, it will reason pretty well based off of that, I recon.
Making a list is one thing, executing a real attack is another.