Prompt Injections for Defense
This seems to work : Researchers from Tracebit on Monday said they found that placing prompt injections alongside passwords, cryptographic keys, and other secrets stored on Amazon Web Services was often all that was needed to shut down attacks from AI hacking agents. The prompts direct the attacking LLM to perform an action forbidden by its guardrails, the safety barriers AI developers erect to…
We haven't written up this one. Schneier on Security has the full story — the link below goes straight to it.
