Author

Yunseung Lee

1 paper indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

#natural language process... Jun 2026

Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense

Across model-level safety on HarmBench and agent-level safety on AgentHarm, Membrane achieves the highest F1 on all six modern jailbreak attacks, and benign refusal on AgentHarm stays at 7-14%, well below the 28-85% range of prior guards.

Minseok Choi, Seung-Moo Yang, Dongjin Kim et al. · arXiv.org · 2 citations