Beyond Attack Success Rate: Temporal Logit Observability for LLM Safety Failures Junyoung Park, Sunghwan Park, Sungyong Joo, Jaewoo LeePreprint, 2026 [arXiv] [Preprint]
A GraphRAG-Based Framework for Interpreting Financial Security Regulations Sungyong Joo, Junyoung Park, Byunghoon Oh, Jaewoo LeePublished: November 01, 2025 [Proceedings] [PDF] [Conference]
Persona Attack: Incremental Memory Injection Jailbreak Attack against Large Language Models Junyoung Park, Yeseul Jang, Sungyong Joo, Byunghoon Oh, Yunseo Han, Sunghwan Park, Jaewoo LeePreprint, 2025 [Preprint]