6 matches found
AutoRAN-public
๐ง AutoRAN: Automated Hijacking of Safety Reasoning in Large Reasoning Models AutoRAN is an automated Hijacking of Safety Reasoning that leverages less-aligned secondary auxiliary models to simulate reasoning traces, generate narrative prompts, and iteratively refine those prompts to bypass safety...
Learning from Failures: A Failure-Driven Prompt Refinement for LLM-Based Vulnerability Analysis
Large Language Models have emerged as promising tools for software vulnerability analysis, but their effectiveness depends heavily on prompt design. Existing research primarily compares prompting strategies using aggregate performance metrics, providing limited insight into why models fail or how...
MAI-2024-0045
This vulnerability in large language models LLMs enables near-perfect jailbreaking through iterative prompt refinement and self-explanation techniques. An attacker can leverage the LLM's own capabilities to refine adversarial prompts by soliciting self-explanations for previous unsuccessful...
MAI-2025-0009
This vulnerability in Large Language Models LLMs enables adversarial reasoning attacks that circumvent established safety protocols, resulting in the generation of harmful responses. The root cause of this vulnerability is the inadequate robustness of current LLM safety measures against iterative...
MT-JailBench: A Modular Benchmark for Understanding Multi-Turn Jailbreak Attacks
Multi-turn jailbreaks exploit the ability of large language models to accumulate and act on conversational context. Instead of stating a harmful request directly, an attacker can gradually steer the conversation toward an unsafe answer. Recent methods demonstrate this risk, but they are usually...
AutoRAN: Weak-To-Strong Jailbreaking of Large Reasoning Models
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...