Clean-label backdoor attack and defense: An examination of language model vulnerability
| Autor: | Zhao, Shuai a, Xu, Xiaoyu a, Xiao, Luwei b, Wen, Jinming c, Tuan, Luu Anh a, ⁎ |
|---|---|
| Zdroj: | In Expert Systems With Applications 15 March 2025 265 |
| Databáze: | ScienceDirect |
| Externí odkaz: |
|
Full Text from ScienceDirect