CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning 事件

CHASE: Adversarial Red-Blue Teaming for Improving LLM Safety using Reinforcement Learning arXiv:2606.05523v1 Announce Type: new Abstract: Despite advances in safety alignment, prompt-rewriting attacks such as persona modulation, fictional framing and persuasion-based reformulation, can bypass safety filters even on frontier models. Existing defenses either rely on non-scalable human curation or white-box optimisation that overfits to specific model internals, leaving aligned models brittle agai