1
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
LLM智能体安全新方案：通过自演进对比记忆机制，让防御系统在动态攻击中持续强化，兼具可塑性与鲁棒性。
arXiv:2606.05743v1 Announce Type: cross Abstract: Despite advances in safety alignment, large language models remain vulnerable to continuously evolvi…