Explainable Graph Attention-Driven Fairness Manipulation for Federated Learning in EdgeIoT
Ref: CISTER-TR-250801 Publication Date: 2025
Explainable Graph Attention-Driven Fairness Manipulation for Federated Learning in EdgeIoT
Ref: CISTER-TR-250801 Publication Date: 2025Abstract:
This paper proposes an innovative adversarial architecture based on Explainable Graph AtTention-embedded autoEncoder (E-GATE), specifically designed to execute fairness manipulation that introduce biasing model updates into the federated learning in edge-based Internet of Things (EdgeIoT). E-GATE aims to generate biasing model updates by maximizing the minimum Kullback-Leibler (KL) divergence between a device’s local model update and the global model. The E-GATE is trained with attention coefficients to obtain the hidden representations of each data feature in the explainable graph. Additionally, the graph autoencoder is incorporated within the E-GATE architecture to manipulatively reconstruct the correlations among model updates. This approach maximizes the reconstruction loss while keeping the biasing model updates undetected. The EGATE attack is implemented using PyTorch, and experimental results demonstrate that it successfully increases the minimum KL divergence of benign model updates by 70.2%, effectively evading detection by existing defense mechanisms.
Kai Li
Jingjing Zheng
Wei Ni
Hailong HuangDocument:
View
DownloadIEEE/CIC International Conference on Communications in China (ICCC) (ICCC), Internet of Things.
Shanghai, China.
Record Date: 10, Aug, 2025