影响力指数

39.54/100

前 14.7%

全站排名 #9,486

发表论文4 篇

平均评分5.5

年均产出1.3 篇/年

Shengfang Zhai

Researcher@National University of Singapore·新加坡·OpenReview

研究方向

AI privacy · Generative models · Backdoor attacks

Silent Leaks: Implicit Knowledge Extraction Attack on RAG Systems

ICLR 2026Poster

DMark: Order-Agnostic Watermarking for Diffusion Large Language Models

ICLR 2026Withdrawn

GuardReasoner-VL: Safeguarding VLMs via Reinforced Reasoning

NeurIPS 2025Poster

合作者 (20)

博后导师3 篇