Federated Deep Learning for Intrusion Detection in Consumer-Centric Internet of Things
Federated Deep Learning for Intrusion Detection in Consumer-Centric Internet of Things
复制标题
DOI：
10.1109/tce.2023.3347170
复制
发表时间：
2024-02
影响因子：
4.3
通讯作者：
S. Popoola;A. Imoize;M. Hammoudeh;B. Adebisi;Olamide Jogunola;A. Aibinu
中科院分区：
文献类型：
--
作者：
S. Popoola;A. Imoize;M. Hammoudeh;B. Adebisi;Olamide Jogunola;A. Aibinu
以消费者为中心的物联网 (CIoT) 将在第五次工业革命（工业 5.0）中发挥关键作用，但它存在的漏洞可能使其容易受到各种网络攻击。最近的研究探索了联邦学习 (FL) 在物联网中保护隐私的入侵检测中的潜力。然而，FL模型的开发依赖于不切实际且不相关的网络流量数据，同时在涵盖的攻击类型和分类场景方面也表现出局限性。在本文中，我们使用三个最新且高度相关的数据集开发联合深度学习（FDL）模型，涵盖广泛的攻击类型以及二元和多类分类场景。我们的研究结果表明，FDL 模型不仅在准确度 $(99.60\pm 0.46\%)$ 、精度 $(92.50\pm 8.40\%)$ 、召回率 $(95.42\pm 6.24\%)$ 和 F1 分数 $(93.51\pm 7.76\%)$ 方面实现了与传统集中式深度学习 (CDL) 模型相当的高分类性能，而且与 CDL 同类产品相比，还表现出卓越的计算效率。 FDL 方法将训练时间减少了 $30.52 - 75.87\%$ 。这些分类性能和计算效率是通过 FDL 中的多轮分布式本地训练实现的。因此，所提出的 FDL 框架为设计和部署弹性 CIoT 提供了强大的安全解决方案。
Consumer-centric Internet of Things (CIoT) will play a pivotal role in the fifth industrial revolution (Industry 5.0) but it exhibits vulnerabilities that can render it susceptible to various cyberattacks. Recent studies have explored the potential of Federated Learning (FL) for privacy-preserving intrusion detection in IoT. However, the development of the FL models relied on unrealistic and irrelevant network traffic data, while also exhibiting limitations in terms of covered attack types and classification scenarios. In this paper, we develop Federated Deep Learning (FDL) models using three recent and highly relevant datasets, covering a wide range of attack types as well as binary and multi-class classification scenarios. Our findings demonstrate that the FDL models not only achieve high classification performance, comparable to traditional Centralized Deep Learning (CDL) models, in terms of accuracy $(99.60\pm 0.46\%)$ , precision $(92.50\pm 8.40\%)$ , recall $(95.42\pm 6.24\%)$ , and F1 score $(93.51\pm 7.76\%)$ but also exhibit superior computational efficiency compared to their CDL counterparts. The FDL approach reduces the training time by $30.52 - 75.87\%$ . These classification performance and computational efficiency were achieved through multiple rounds of distributed local training in FDL. Therefore, the proposed FDL framework presents a robust security solution for designing and deploying a resilient CIoT.