作者位次 #4/5ACL 2026Poster· Natural Language Processing
S afety M em: Adaptive Jailbreak Defense via Dual-Component Safety Memory
Hao Wang · Ziyi Ni · Huacan Wang · Pin Lyu · Lei Sha
摘要
Current defenses for Large Language Models (LLMs) often suffer from a ”memory gap”: parameter-modifying methods are computationally rigid, while inference-time filters cannot retain or reuse defense knowledge across interactions. To address this, we propose SafetyMem, a novel framework that secur...