KDA: A Knowledge-Distilled Attacker for Generating Diverse Prompts to Jailbreak LLMs

Fuente: arXiv

Saved in:

Bibliographic Details
Main Authors:	Liang, Buyun, Chan, Kwan Ho Ryan, Thaker, Darshan, Luo, Jinqi, Vidal, René
Format:	Preprint
Published:	2025
Subjects:	Cryptography and Security Artificial Intelligence Computation and Language Machine Learning
Online Access:	Acceder al recurso
Tags:	Add Tag No Tags, Be the first to tag this record!

Internet

https://arxiv.org/abs/2502.05223