LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models
Researchers have developed LASH, a novel framework designed to enhance the jailbreaking of large language models. LASH adaptively combines outputs from multiple existing attack methods, treating them as seed prompts. This approach leverages the complementary strengths of different attack families to improve success rates against various models and harm categories. In evaluations on the JailbreakBench dataset, LASH achieved high attack success rates with significantly fewer queries compared to state-of-the-art baselines. AI
IMPACT Introduces a more effective method for red-teaming LLMs, potentially accelerating the discovery and patching of safety vulnerabilities.