Lightweight defense mechanism against adversarial attacks via adaptive pruning and robust distillation
Adversarial training is one of the commonly used defense methods against adversarial attacks, by incorporating adversarial samples into the training process.However, the effectiveness of adversarial training heavily relied on the size of the trained model.Specially, the size of trained models genera...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
POSTS&TELECOM PRESS Co., LTD
2022-12-01
|
| Series: | 网络与信息安全学报 |
| Subjects: | |
| Online Access: | https://www.infocomm-journal.com/cjnis/CN/10.11959/j.issn.2096-109x.2022074 |