Adversary Aware Continual Learning
Continual learning approaches are useful to help a model learn new information or new tasks sequentially, while also retaining the previously acquired information. However, such approaches are known to be extremely vulnerable to the adversarial backdoor attacks, where an intelligent adversary can in...
שמור ב:
| Principais autores: | , |
|---|---|
| פורמט: | Artigo |
| שפה: | Inglês |
| יצא לאור: |
IEEE
2024-01-01
|
| סדרה: | IEEE Access |
| נושאים: | |
| גישה מקוונת: | https://ieeexplore.ieee.org/document/10666674/ |
| תגים: |
אין תגיות, היה/י הראשונ/ה לתייג את הרשומה!
|