FedID : Enhancing Federated Learning Security Through Dynamic Identification
Federated learning (FL), recognized for its decentralized and privacy-preserving nature, faces vulnerabilities to backdoor attacks that aim to manipulate the model's behavior on attacker-chosen inputs. Most existing defenses based on statistical differences take effect only against specific att...
Ausführliche Beschreibung
Bibliographische Detailangaben
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence. - 1979. - 47(2025), 10 vom: 01. Sept., Seite 8907-8922
|
|---|
| 1. Verfasser: |
Huang, Siquan
(VerfasserIn) |
|---|
| Weitere Verfasser: |
Li, Yijiang,
Chen, Chong,
Gao, Ying,
Hu, Xiping |
|---|
| Format: | Online-Aufsatz
|
|---|
| Sprache: | English |
|---|
| Veröffentlicht: |
2025
|
|---|
| Zugriff auf das übergeordnete Werk: | IEEE transactions on pattern analysis and machine intelligence
|
|---|
| Schlagworte: | Journal Article |
|---|