Detection of Malicious Clients in Federated Learning Using Graph Neural Network

Federated Learning (FL) facilitates decentralized model training without the exchange of raw data, thereby guaranteeing privacy. However, due to its distributed nature, this paradigm is susceptible to adversarial threats such as sign-flipping attacks, in which malicious clients reverse model paramet...

Cijeli opis

Bibliografski detalji

Glavni autori:	Anee Sharma, Ningrinla Marchang
Format:	Artigo
Jezik:	Inglês
Izdano:	IEEE 2025-01-01
Serija:	IEEE Access
Teme:	Federated learning anomaly detection graph neural networks sign-flipping attacks graph attention networks malicious clients
Online pristup:	https://ieeexplore.ieee.org/document/10980311/
Oznake:	Dodaj oznaku Bez oznaka, Budi prvi tko označuje ovaj zapis!