Changjiang Li

~Changjiang_Li1

4

论文总数

2.0

年均投稿

5.4

平均评分

接收情况2/4

会议分布

ICLR

4

发表论文 (4 篇)

20253 篇

Your Agent Can Defend Itself against Backdoor Attacks

ICLR 2025withdrawn

RAPID: Retrieval Augmented Training of Differentially Private Diffusion Models

ICLR 2025Poster

RobustKV: Defending Large Language Models against Jailbreak Attacks via KV Eviction

ICLR 2025Poster

20241 篇

A Change of Heart: Backdoor Attacks on Security-Centric Diffusion Models

ICLR 2024Rejected

合作者 (9)

Bochuan Cao2 篇

Jinghui Chen2 篇

Jiacheng Liang2 篇

Tanqiu Jiang2 篇

Yuhui Wang1 篇