Hacker News new | past | comments | ask | show | jobs | submit login

Please elaborate, how are LLMs going to provide a "more sophisticated" class of automated attacks, and how are toy countermeasures like ZIP bombs going to defend against these "sophisticated" attacks?

I could believe you if you said that ZIP bombs are perhaps mildly effective against script kiddies using ChatGPT to generate a naive, simplistic automated scanners that are susceptible to being "zip bombed". The other way around? Not so much.

These zip bombs are trivial to defend against as an attacker, e.g. by inspecting the payload while you're decompressing it to see if it matches some expected output (an <html> tag, for example) or by aborting after the decompressed size exceeds some limit (10 MB is way more HTML than you'd typically expect, for example).




I didn't say a zip bomb is effective against LLMs, I said active countermeasures in general


Do you mind elaborating, how are LLMs going to help with sophisticated attacks and what kind of countermeasures do you have in mind?




Consider applying for YC's Spring batch! Applications are open till Feb 11.

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: