影响力指数

12.5/100

超过 38.8%

全站排名 #39,421

发表论文3 篇

平均评分5.6

年均产出1.5 篇/年

Qizhang Li

PhD student@Harbin Institute of Technology·中国·OpenReview

Deciphering the Chaos: Enhancing Jailbreak Attacks via Adversarial Prompt Translation

ICLR 2025Rejected

DualAug: Exploiting Additional Heavy Augmentation with OOD Data Rejection

ICLR 2024Rejected

Improved Generation of Adversarial Examples Against Safety-aligned LLMs

NeurIPS 2024Poster

合作者 (7)

博士导师1 篇