Improving Fast Adversarial Training With Prior-Guided Knowledge
Fast adversarial training (FAT) is an efficient method to improve robustness in white-box attack scenarios. However, the original FAT suffers from catastrophic overfitting, which dramatically and suddenly reduces robustness after a few training epochs. Although various FAT variants have been propose...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 46(2024), 9 vom: 23. Aug., Seite 6367-6383
|
|---|
| 1. Verfasser: |
Jia, Xiaojun
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Zhang, Yong,
Wei, Xingxing,
Wu, Baoyuan,
Ma, Ke,
Wang, Jue,
Cao, Xiaochun |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2024
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|