3 papers
cs.CR2026
Defending against Backdoor Attacks via Module Switching
Weijun Li, Ansh Arora, Xuanli He +2
Backdoor attacks pose a serious threat to deep neural networks (DNNs), allowing adversaries to implant triggers for hidden behaviors in inference. Defending against such vulnerabil…
cs.CR2026
Beyond Theoretical Bounds: Empirical Privacy Loss Calibration for Text Rewriting Under Local Differential Privacy
Weijun Li, Arnaud Grivet Sébert, Qiongkai Xu +2
The growing use of large language models has increased interest in sharing textual data in a privacy-preserving manner. One prominent line of work addresses this challenge through…
cs.CL2025
Cut the Deadwood Out: Backdoor Purification via Guided Module Substitution
Yao Tong, Weijun Li, Xuanli He +2
Model NLP models are commonly trained (or fine-tuned) on datasets from untrusted platforms like HuggingFace, posing significant risks of data poisoning attacks. A practical yet und…