DLP: towards active defense against backdoor attacks with decoupled learning process
Abstract Deep learning models are well known to be susceptible to backdoor attack, where the attacker only needs to provide a tampered dataset on which the triggers are injected. Models trained on the dataset will passively implant the backdoor, and triggers on the input can mislead the models durin...
| 发表在: | Cybersecurity |
|---|---|
| Main Authors: | , |
| 格式: | 文件 |
| 语言: | 英语 |
| 出版: |
SpringerOpen
2023-05-01
|
| 主题: | |
| 在线阅读: | https://doi.org/10.1186/s42400-023-00141-4 |