多云联邦学习中兼顾模型精度与通信成本，防恶意攻击
Cost-TrustFL: Cost-Aware Hierarchical Federated Learning with Lightweight Reputation Evaluation across Multi-Cloud
- 分层架构+梯度近似沙普利值，轻量评估参与方信誉
- 跨云通信减少32%，在30%恶意节点下仍达86.7%准确率
- 适合资源受限、需控成本的多云联邦学习场景
多云环境下的联邦学习面临非独立同分布数据、恶意参与者检测及高昂跨云通信成本（如出站费用）等挑战。现有拜占庭鲁棒方法主要关注模型精度，忽视了跨云数据传输的经济代价。本文提出Cost-TrustFL框架，联合优化模型性能与通信成本，并提供对投毒攻击的强防御能力。我们设计基于梯度的近似沙普利值计算方法，将复杂度从指数级降至线性，实现轻量级信誉评估。成本感知聚合策略优先选择云内通信，减少昂贵的跨云数据传输。在CIFAR-10和FEMNIST数据集上的实验表明，当存在30%恶意客户端时，Cost-TrustFL仍可达到86.7%准确率，相比基线方法通信成本降低32%。该框架在不同非独立同分布程度和攻击强度下保持稳定性能，适用于真实多云部署。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。