Li Liu

~Li_Liu8

5

论文总数

2.5

年均投稿

5.4

平均评分

接收情况2/5

会议分布

ICLR

4

NeurIPS

1

发表论文 (5 篇)

20252 篇

New Paradigm of Adversarial Training: Breaking Inherent Trade-Off between Accuracy and Robustness via Dummy Classes

ICLR 2025Rejected

Activation Gradient based Poisoned Sample Detection Against Backdoor Attacks

ICLR 2025Poster

20243 篇

Unveiling and Mitigating Backdoor Vulnerabilities based on Unlearning Weight Changes and Backdoor Activeness

NeurIPS 2024Poster

Robust Backdoor Attack with Visible, Semantic, Sample-specific and Compatible Triggers

ICLR 2024Rejected

Directional Rank Reduction for Backdoor Defense

ICLR 2024Rejected

合作者 (20)

Baoyuan Wu2 篇

Shaokui Wei2 篇

Jindong Wang1 篇

Runkai Zheng1 篇

Xuanchang Xu1 篇

Hongrui Chen1 篇