Dasol Choi
2 indexed papers
Publications per year
Top categories
Frequent co-authors
Research Timeline
The paper introduces 'brittle safety,' a failure mode where aligned language models fail to adapt their safety behavior when a situational context changes, and proposes state-aware validation to detect these failures.
The paper presents a benchmark for testing the robustness of large language model agents in safety-critical systems under sustained, adaptive adversarial pressure.
Papers
LLM agent safety, multi-turn red-teaming, jailbreak benchmarks, adversarial robustness, safety-critical systems
Hanwool Lee, Dasol Choi, Bokyeong Kim, Seung Geun Kim +1 more
The paper presents a benchmark for testing the robustness of large language model agents in safety-critical systems under sustained, adaptive adversarial pressure.