AI-powered Bing Chat spills its secrets via prompt injection attack

Re:AI-powered Bing Chat spills its secrets via prompt inject... by swatcoder on Monday February 13, 2023 @05:33PM (#34781827)

It’s so interesting to see how some people can see boundless possibilities in the future of this technology, decrying any discussion of limitations as premature, but then write off the scope of its security challenges as trivial.

But it’s way more important to keep an open and imaginative mind regarding security than it is about anything the tech might enable. The uses of the effective tech are inevitable, whatever they are, but security posturing only comes from attention and insight.

[ Parent | on HN ]

Re:AI-powered Bing Chat spills its secrets via prompt inject... by VectorLock on Monday February 13, 2023 @06:35PM (#34782600)

Security assessment involves analyzing impact. I think in this case the impacts are "access to the model pre-prompting" which is low impact if it doesn't have secrets in it and "make the model say potentially inappropriate things that would make the company behind it look bad" which you might say has a higher but in the grand scheme of things not a huge impact.

[ Parent | on HN ]

Re:AI-powered Bing Chat spills its secrets via prompt inject... by imtringued on Tuesday February 14, 2023 @06:18AM (#34787879)

>I think in this case the impacts are "access to the model pre-prompting" which is low impact if it doesn't have secrets in it

Except in the case of fine-tuned models where the training samples and pre-prompts are the secret sauce...

[ Parent | on HN ]