Interesting Paper Exploring Prompt Injection
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 scaffoldi…
Seguir leyendo en Schneier on Security →
Pronto, la IA de LaiaDesk publicará aquí el análisis completo de qué significa esta noticia para tu sector.
Fuente original: Schneier on Security
Conversación
Inicia sesión para comentar y reaccionar.
EntrarSé el primero en comentar.