Qiongkai Xu

~Qiongkai_Xu1

4

论文总数

2.0

年均投稿

4.9

平均评分

接收情况0/4

会议分布

ICLR

3

NeurIPS

1

发表论文 (4 篇)

20252 篇

TuBA: Cross-Lingual Transferability of Backdoor Attacks in LLMs with Instruction Tuning

ICLR 2025withdrawn

Defending Deep Neural Networks against Backdoor Attacks via Module Switching

NeurIPS 2025Rejected

20242 篇

FLAT-Chat: A Word Recovery Attack on Federated Language Model Training

ICLR 2024Rejected

Generative Models are Self-Watermarked: Intellectual Property Declaration through Re-Generation

ICLR 2024Rejected

合作者 (12)

Trevor Cohn2 篇

Ansh Arora1 篇

Olga Ohrimenko1 篇

Aditya Desu1 篇