针对物联网异常检测，提出高效个性化联邦PCA方法
Efficient Personalized Federated PCA with Manifold Optimization for IoT Anomaly Detection
- 通过$\\\ ext{l}_1$和$\\\\text{l}_{2,1}$范数实现局部稀疏性与鲁棒性
- 在多个物联网安全场景中达到更高准确率和F1分数
- 适合资源受限的分布式物联网环境中的异常检测
物联网网络因分布特性与资源限制面临日益严峻的安全威胁。尽管联邦学习（FL）作为隐私保护框架在分布式物联网环境中备受关注，但现有联邦主成分分析（PCA）方法缺乏个性化与鲁棒性的结合，严重影响异常检测效果。为此，本文提出一种高效的个性化联邦PCA（FedEP）方法用于物联网异常检测。该模型通过引入$\\\\ell_1$-范数实现元素级稀疏性以获得本地化表示，同时利用$\\\\ell_{2,1}$-范数实现行级稀疏性以保持鲁棒性。为求解该非凸问题，我们设计了一种基于交替方向乘子法（ADMM）的流形优化算法，并具备严格的理论收敛性保证。实验结果表明，所提方法优于当前最优的FedPG，在多种物联网安全场景中均取得优异的F1得分与准确率。代码将公开于https://github.com/xianchaoxiu/FedEP。
原文摘要 · Abstract (English)
Internet of things (IoT) networks face increasing security threats due to their distributed nature and resource constraints. Although federated learning (FL) has gained prominence as a privacy-preserving framework for distributed IoT environments, current federated principal component analysis (PCA) methods lack the integration of personalization and robustness, which are critical for effective anomaly detection. To address these limitations, we propose an efficient personalized federated PCA (FedEP) method for anomaly detection in IoT networks. The proposed model achieves personalization through introducing local representations with the $\ell_1$-norm for element-wise sparsity, while maintaining robustness via enforcing local models with the $\ell_{2,1}$-norm for row-wise sparsity. To solve this non-convex problem, we develop a manifold optimization algorithm based on the alternating direction method of multipliers (ADMM) with rigorous theoretical convergence guarantees. Experimental results confirm that the proposed FedEP outperforms the state-of-the-art FedPG, achieving excellent F1-scores and accuracy in various IoT security scenarios. Our code will be available at \href{https://github.com/xianchaoxiu/FedEP}{https://github.com/xianchaoxiu/FedEP}.
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。