AutoRAN: Weak-to-Strong Jailbreaking of Large Reasoning Models
원문 초록
This paper presents AutoRAN, the first automated, weak-to-strong jailbreak attack framework targeting large reasoning models (LRMs). At its core, AutoRAN leverages a weak, less-aligned reasoning model to simulate the target model's high-level reasoning structures, generates narrative prompts, and iteratively refines candidate prompts by incorporating the target model's intermediate reasoning steps. We evaluate AutoRAN against state-of-the-art LRMs including GPT-o3/o4-mini and Gemini-2.5-Flash across multiple benchmark datasets (AdvBench, HarmBench, and StrongReject). Results demonstrate that AutoRAN achieves remarkable success rates (approaching 100%) within one or a few turns across different LRMs, even when judged by a robustly aligned external model. This work reveals that leveraging weak reasoning models can effectively exploit the critical vulnerabilities of much more capable reasoning models, highlighting the need for improved safety measures specifically designed for reasoning-based models. The code for replicating AutoRAN and running records are available at: (https://github.com/JACKPURCELL/AutoRAN-public). (warning: this paper contains potentially harmful content generated by LRMs.)
함께 살펴볼 논문
공통 태그를 근거로 연결했습니다. 실제 인용 관계나 논문의 우수성을 뜻하지 않습니다.
공통 태그로 연결된 공개 논문이 아직 없습니다.
토론
이 논문과 연결된 포럼 글이 아직 없습니다.