影响力指数

-/100

发表论文2 篇

平均评分2.8

年均产出2.0 篇/年

Xiaolei Liu

Researcher@China Academy of Engineering Physics·中国·OpenReview

研究方向

AI Security · Trusted LLM

CoaxChain: Semantically Progressive Multi-turn Jailbreak Attacks on Large Language Models

ICLR 2026Rejected

TRIDENT: Three-Dimensional Data Copyright Infringement Detection in LLMs

ICLR 2026Rejected

合作者 (12)