影响力指数

-/100

发表论文2 篇

平均评分4.1

年均产出1.0 篇/年

Rui Wen

Assistant Professor@Institute of Science Tokyo·日本·OpenReview

研究方向

Large Language Model · Data poisoning · Machine learning security and privacy

IAAgent: Autonomous Inference Attacks Against ML Services With LLM-Based Agents

ICLR 2026Withdrawn

Last One Standing: A Comparative Analysis of Security and Privacy of Soft Prompt Tuning, LoRA, and In-Context Learning

ICLR 2024Rejected

合作者 (6)

博士导师2 篇