LASH: Adaptive Semantic Hybridization for Black-Box Jailbreaking of Large Language Models

ArXi:2605.21362v1 Announce Type: new Jailbreak attacks expose a persistent gap between the intended safety behavior of aligned large language models and their behavior under adversarial prompting. Existing automated methods are increasingly effective but each commits to a single attack family (e.g., one refinement loop, one tree search, one mutation space, or one strategy library) and no single family dominates: the best-performing method shifts across target models and harm categories, suggesting complementary strengths that per-prompt composition could exploit. We.