GReAT: A Graph Regularized Adversarial Training Method
This paper presents GReAT (Graph Regularized Adversarial Training), a novel regularization method designed to enhance the robust classification performance of deep learning models. Adversarial examples, characterized by subtle perturbations that can mislead models, pose a significant challenge in ma...
Gespeichert in:
| Hauptverfasser: | , |
|---|---|
| Format: | Artigo |
| Sprache: | Inglês |
| Veröffentlicht: |
IEEE
2024-01-01
|
| Schriftenreihe: | IEEE Access |
| Schlagworte: | |
| Online-Zugang: | https://ieeexplore.ieee.org/document/10516321/ |
| Tags: |
Keine Tags, Fügen Sie das erste Tag hinzu!
|