Kryptovalutaticker:
sysadmin från Schneier on Security

Interesting Paper Exploring Prompt Injection

Bruce Schneier
Thursday at 11:23
4 Visningar
0 Kommentarer

This is a fascinating explotation of how LLMs fall for prompt injection attacks. It turns out that they learn to recognize the style of text in different role/instruction blocks, and not just the tags. Their conclusion: Role tags were a formatting trick that became the security architecture and the cognitive scaffolding of modern LLMs. We’ve...

Läs hela artikeln hos källan.

Var detta hjälpsamt?
Dela:

Kommentarer (0)

Vänligen logga in för att publicera en kommentar

Inga kommentarer ännu. Bli först med att kommentera!