News for hackers. Stuff that matters.
Re:Delimiters won’t save you from prompt injection by kryogen1c on Saturday May 13, 2023 @08:34AM (#35927756)
Isn't this security through obfuscation? Doesn't it shift the risk instead of eliminating it? That's fine if that's the intention, but that's a different risk mitigation strategy.

The post you replied to is saying it's categorically impossible to have an injection filter when user input interacts with executable statements.

Re:Delimiters won’t save you from prompt injection by r13a on Saturday May 13, 2023 @12:39PM (#35930040)
> Doesn't it shift the risk > instead of eliminating it?

Yes it's exactly that.

Of course I'm not trying to argue that there's a magic stick to make prompt injection just go away. My point is that prompt injection is so dangerous because we're letting the user directly interact with such a powerful beast as SOTA LLM.

By filtering prompts and answers by much less powerful but more specialized models we are heavily mitigating risks. But injection risks will still be there just not as wide open injections avenues as today.