Yun Shen

~Yun_Shen3

4

论文总数

2.0

年均投稿

5.3

平均评分

接收情况1/4

会议分布

ICLR

3

ICML

1

发表论文 (4 篇)

20251 篇

The Ripple Effect: On Unforeseen Complications of Backdoor Attacks

ICML 2025Poster

20243 篇

Composite Backdoor Attacks Against Large Language Models

ICLR 2024withdrawn

Prompt Backdoors in Visual Prompt Learning

ICLR 2024withdrawn

Robustness Over Time: Understanding Adversarial Examples’ Effectiveness on Longitudinal Versions of Large Language Models

ICLR 2024Rejected

合作者 (12)

Yang Zhang4 篇

Michael Backes3 篇

Zhengyu Zhao3 篇

Tianshuo Cong1 篇

Yugeng Liu1 篇

Hanxiao Chen1 篇