News for hackers. Stuff that matters.
Re:Multi-modal prompt injection image attacks against GPT-4V by spdustin on Saturday October 14, 2023 @11:43AM (#37881365)
I use it all the time to embed graphviz diagrams by instructing it to url-encode them and include it in the query string to a rendering endpoint. It spooked me enough that I added proxy layer to verify that it’s not rendering what appears to be a chat or PII.

The world isn’t ready for LLMs unleashed like this. Any plugin could do the same thing, and exfiltrate any part of the chat context with very little instruction engineering to bypass what things guardrails exist on the plugins side.

There are no comments on this comment yet.