연구실 논문 ICLR 2026 Accept
연구실 논문 “SlotGCG, Exploiting the Positional Vulnerability in LLMs for Jailbreak Attacks"이 The 14th International Conference on Learning Representations (ICLR 2026)에 Accept 되었습니다.
Author: Seungwon Jeong, Jiwoo Jeong, Hyeonjin Kim, Yunseok Lee, Woojin Lee*
Information:
- Conference: The 14th International Conference on Learning Representations (ICLR 2026)
- Date: 2026년 4월 23일 - 27일
- Location: Riocentro Convention and Event Center, Rio de Janeiro, Brazil