AAAI 2025 paper

Backdoor Token Unlearning: Exposing and Defending Backdoors in Pretrained Language Models

0citations

0

Citations

#1168

in AAAI 2025

of 3028 papers

4

Authors

1

Data Points

Authors

Peihai Jiang Xixiang Lyu Yige Li Jing Ma

Citation History

Jan 28, 2026

0