Enhanced federated anomaly detection through autoencoders using summary statistics-based thresholding
Abstract In Federated Learning, Anomaly Detection poses significant challenges due to the decentralized nature of data, especially under Non-IID distributions. This study proposes a federated threshold calculation method that aggregates summary statistics from normal and anomalous data across client...
Gorde:
| Egile Nagusiak: | , , |
|---|---|
| Formatua: | Artigo |
| Hizkuntza: | Inglês |
| Argitaratua: |
Nature Portfolio
2024-11-01
|
| Saila: | Scientific Reports |
| Gaiak: | |
| Sarrera elektronikoa: | https://doi.org/10.1038/s41598-024-76961-2 |
| Etiketak: |
Etiketarik gabe, Izan zaitez lehena erregistro honi etiketa jartzen!
|