Interpolated Joint Space Adversarial Training for Robust and Generalizable Defenses
Adversarial training (AT) is considered to be one of the most reliable defenses against adversarial attacks. However, models trained with AT sacrifice standard accuracy and do not generalize well to unseen attacks. Recent works show generalization improvement with adversarial samples under unseen th...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 45(2023), 11 vom: 19. Nov., Seite 13054-13067
|
|---|
| 1. Verfasser: |
Lau, Chun Pong
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Liu, Jiang,
Souri, Hossein,
Lin, Wei-An,
Feizi, Soheil,
Chellappa, Rama |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2023
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|