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...
Sparad:
| Huvudupphov: | , |
|---|---|
| Materialtyp: | Artigo |
| Språk: | Inglês |
| Utgiven: |
IEEE
2024-01-01
|
| Serie: | IEEE Access |
| Ämnen: | |
| Länkar: | https://ieeexplore.ieee.org/document/10666674/ |
| Taggar: |
Inga taggar, Lägg till första taggen!
|