139 citations · 142 across the 3 of their papers we have counts for
3 papers
cs.CR2025★ 1 cited
Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models
Peihai Jiang, Xixiang Lyu, Yige Li +1
Supervised fine-tuning has become the predominant method for adapting large pretrained models to downstream tasks. However, recent studies have revealed that these models are vulne…
cs.CR2021★ 2 cited
A Novel Variable K-Pseudonym Scheme Applied to 5G Anonymous Access Authentication
Dong Ma, Xixiang Lyu, Renpeng Zou
Anonymous access authentication schemes provide users with massive application services while protecting the privacy of users' identities. The identity protection schemes in 3G and…
cs.LG2021★ 139 cited
Neural Attention Distillation: Erasing Backdoor Triggers from Deep Neural Networks
Yige Li, Xixiang Lyu, Nodens Koren +3
Deep neural networks (DNNs) are known vulnerable to backdoor attacks, a training time attack that injects a trigger pattern into a small proportion of training data so as to contro…