Cost-TrustFL: Cost-Aware Hierarchical Federated Learning with Lightweight Reputation Evaluation across Multi-Cloud

TL;DR

Cost-TrustFL is a hierarchical federated learning framework that balances model accuracy, robustness against attacks, and communication costs in multi-cloud environments, using lightweight reputation evaluation and cost-aware aggregation.

Contribution

It introduces a cost-aware hierarchical federated learning framework with a novel lightweight reputation evaluation method for multi-cloud settings.

Findings

Achieves 86.7% accuracy with 30% malicious clients

Reduces communication costs by 32% compared to baselines

Maintains stable performance across non-IID data and attack variations

Abstract

Federated learning across multi-cloud environments faces critical challenges, including non-IID data distributions, malicious participant detection, and substantial cross-cloud communication costs (egress fees). Existing Byzantine-robust methods focus primarily on model accuracy while overlooking the economic implications of data transfer across cloud providers. This paper presents Cost-TrustFL, a hierarchical federated learning framework that jointly optimizes model performance and communication costs while providing robust defense against poisoning attacks. We propose a gradient-based approximate Shapley value computation method that reduces the complexity from exponential to linear, enabling lightweight reputation evaluation. Our cost-aware aggregation strategy prioritizes intra-cloud communication to minimize expensive cross-cloud data transfers. Experiments on CIFAR-10 and FEMNIST datasets demonstrate that Cost-TrustFL achieves 86.7% accuracy under 30% malicious clients while reducing communication costs by 32% compared to baseline methods. The framework maintains stable performance across varying non-IID degrees and attack intensities, making it practical for real-world multi-cloud deployments.