Seungbin Yang
1 indexed paper
Recent (6 mo)
1With code
0Influential cites
0Benchmarked
0Publications per year
126
Top categories
Crypto×1NLP×1
Frequent co-authors
Research Timeline
2026
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
Membrane introduces a self-evolving guardrail using Contrastive Safety Memory (CSM) that generalizes across topical jailbreak variants, achieving superior safety performance while minimizing benign refusal rates.
Highlighted terms show continued research focus across papers
Papers
cs.CRcs.CLRecentJun 4, 2026
Membrane: A Self-Evolving Contrastive Safety Memory for LLM Agent Defense
Minseok Choi, Seungbin Yang, Dongjin Kim, Subin Kim +4 more
Membrane introduces a self-evolving guardrail using Contrastive Safety Memory (CSM) that generalizes across topical jailbreak variants, achieving superior safety performance while minimizing benign re…
View →