Security News > 2024 > May > LLMs’ Data-Control Path Insecurity

Unlike the phone system, we can't separate an LLM's data from its commands.

One of the enormously powerful features of an LLM is that the data affects the code.

We're getting better at creating LLMs that are resistant to these attacks.

We're building systems that clean up inputs, both by recognizing known prompt-injection attacks and training other LLMs to try to recognize what those attacks look like.

Engineers will be tempted to grab for LLMs because they are general-purpose hammers; they're easy to use, scale well, and are good at lots of different tasks.

Until then we're going to have to think carefully about using LLMs in potentially adversarial situationslike, say, on the Internet.

News URL

https://www.schneier.com/blog/archives/2024/05/llms-data-control-path-insecurity.html