Semisupervised Federated-Learning-Based Intrusion Detection Method for Internet of Things

Ruijie Zhao, Yijun Wang, Zhi Xue, Tomoaki Ohtsuki, Bamidele Adebisi, Guan Gui

研究成果: Article査読

25 被引用数 (Scopus)


Federated learning (FL) has become an increasingly popular solution for intrusion detection to avoid data privacy leakage in Internet of Things (IoT) edge devices. Existing FL-based intrusion detection methods, however, suffer from three limitations: 1) model parameters transmitted in each round may be used to recover private data, which leads to security risks; 2) not independent and identically distributed (non-IID) private data seriously adversely affect the training of FL (especially distillation-based FL); and 3) high communication overhead caused by the large model size greatly hinders the actual deployment of the solution. To address these problems, this article develops an intrusion detection method based on a semisupervised FL scheme via knowledge distillation. First, our proposed method leverages unlabeled data via distillation method to enhance the classifier performance. Second, we build a model based on convolutional neural networks (CNNs) for extracting deep features of the traffic packets, and take this model as both the classifier network and discriminator network. Third, the discriminator is designed to improve the quality of each client's predicted labels, and to avoid the failure of distillation training caused by a large number of incorrect predictions under private non-IID data. Moreover, the combination of the hard-label strategy and voting mechanism further reduces communication overhead. The experiments on the real-world traffic data set with three non-IID scenarios show that our proposed method can achieve better detection performance as well as lower communication overhead than state-of-the-art methods.

ジャーナルIEEE Internet of Things Journal
出版ステータスPublished - 2023 5月 15

ASJC Scopus subject areas

  • 情報システム
  • 信号処理
  • ハードウェアとアーキテクチャ
  • コンピュータ ネットワークおよび通信
  • コンピュータ サイエンスの応用


「Semisupervised Federated-Learning-Based Intrusion Detection Method for Internet of Things」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。