Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs 文章

ArXiv CS.AI2026-06-02NEWSen作者: Alexander Panfilov, Peter Romov, Igor Shilov, Yves-Alexandre de Montjoye, Jonas Geiping, Maksym Andriushchenko
查看原文 →
关系图谱

Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs · 相关技术

相关技术

adversarial attacksprompt injectionwhite-box jailbreakingLLM