Conference
Open access
2026
SafetyMem: Adaptive Jailbreak Defense via Dual-Component Safety Memory
This work proposes Safet-yMem, a novel framework that secures LLMs through a dual-component safety memory sys-tem, and introduces an adversarial memory expansion mechanism that proactively generates challenging variants to solidify these memories.
Hao Wang, Ziyi Ni, Huacan Wang et al.
· Annual Meeting of the Associ... · 0 citations