Edge Device Identification Based on Federated Learning and Network Traffic Feature Engineering

IEEE Transactions on Cognitive Communications and Networking, vol. 8, pp. 1898–1909

Abstract

With the ubiquitous deployment and applications of Internet of Things (IoT), security issues pose a critical challenge to IoT devices. External attackers often utilize vulnerable IoT devices to invade the target’s internal network and then further cause a security threat to the whole network. To prevent such attacks, it is necessary to develop a security mechanism to control the access of suspicious IoT devices and manage the internal devices. In recent years, deep learning (DL) algorithm has been widely used in the field of edge device identification (EDI), and has made great achievements. However, these previous methods are essentially centralized learning-based EDI (CentEDI) that trains all data together, which can not guarantee data security and not conducive to deployment on edge devices. To address this problem, we introduce a federated learning-based EDI (FedeEDI) method via network traffic to automatically identify edge devices connected to the whole network. Experimental results show that the training efficiency of our proposed FedeEDI method is much higher than that of the CentEDI method, although its classification accuracy is slightly reduced. In contrast to the CentEDI method, the proposed FedeEDI method has two main advantages: faster training speed and safer training process.

Authors 8

1. Zhimin He

   Nanjing University of Posts and Telecommunications

   Affiliation as printed

   College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China

2. Jie Yin

   Jiangsu Police Officer College · Nanjing University

   Affiliation as printed

   Department of Computer Information and Cyber Security, Jiangsu Police Institute, Nanjing, China

   Key Laboratory of Digital Forensics of Jiangsu Provincial Public Security Department, and State Key Laboratory for Novel Software Technology, Jiangsu Province Electronic Data Forensics and Analysis Engineering Research Center, Nanjing University, Nanjing, China

3. Yu Wang

   Nanjing University of Posts and Telecommunications

   Affiliation as printed

   College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China

4. Guan Gui

   Nanjing University of Posts and Telecommunications

   Affiliation as printed

   College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China

5. Bamidele Adebisi

   Manchester Metropolitan University

   Affiliation as printed

   Department of Engineering, Faculty of Science and Engineering, Manchester Metropolitan University, Manchester, U.K

6. Tomoaki Otsuki Ohtsuki

   Keio University

   Affiliation as printed

   Department of Information and Computer Science, Keio University, Yokohama, Japan

7. Haris Gacanin Aachen Faculty of Electrical Engineering and Information Technology

   RWTH Aachen University

   Affiliation as printed

   Faculty of Electrical Engineering and Information Technology, RWTH Aachen University, Aachen, Germany

8. Hikmet Sari

   Nanjing University of Posts and Telecommunications

   Affiliation as printed

   College of Telecommunications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing, China