Physical Layer Authentication for Mission Critical Machine Type Communication Using Gaussian Mixture Model Based Clustering

Abstract

Abstract-The application of Mission Critical Machine Type Communication (MC-MTC) in wireless systems is currently a hot research topic. Wireless systems are considered to provide numerous advantages over wired systems in e.g. industrial applications such as closed loop control. However, due to the broadcast nature of the wireless channel, such systems are prone to a wide range of cyber attacks. These range from passive eavesdropping attacks to active attacks like data manipulation or masquerade attacks. Therefore it is necessary to provide reliable and efficient security mechanisms. Some of the most important security issues in such a system are to ensure integrity as well as authenticity of exchanged messages over the air between communicating devices. In the present work, an approach on how to achieve this goal in MC-MTC systems based on Physical Layer Security (PHYSEC) is presented. A new method that clusters channel estimates of different transmitters based on a Gaussian Mixture Model is applied for that purpose. Further, an experimental proof-ofconcept evaluation is given and we compare the performance of our approach with a mean square error based detection method.

The Role of Blockchain in 6G: Challenges, Opportunities and Research Directions

“…First, at the physical layer, AI and machine learning techniques have been shown to improve channel coding [28], ranging and obstacle detection [29], and physical layer security [30]. Research in each of these domains is still in a preliminary stage and requires further investigations.…”

Putting Things in Context: Securing Industrial Authentication with Context Information

“…If strong security is needed, the tabled PC could automatically scan his iris to get a second factor. Furthermore, physical attributes of devices or wireless channels can be used for strong, automated authentication and encryption (Lipps et al 2018;Weinand et al 2017). Furthermore, integrating context into an aggregation model can aid in intrusion detection, especially for heterogeneous networks (Duque Anton et al 2017c).…”

A Lightweight Intelligent Authentication Approach for Intrusion Detection

“…Physical layer authentication (PLA), which safeguards communications by using the intrinsic characteristics of wireless channels, is a promising lightweight security method [6]. In previous studies, a number of approaches based on artificial intelligence algorithms, including Support Vector Machine (SVM) [7], Gaussian Mixture Model (GMM) [8], [9], Genetic Algorithms [10], Random Forest [11] and others [12]- [14], have been widely used in PLA technologies. For example, an SVM-based learning method was designed to improve the detection accuracy of the authentication scheme [15].…”

“…Nevertheless, machine learning-assisted PLA solutions are facing both new challenges and opportunities when we consider the time-varying nature of wireless networks. For example, the channel-based PLA scheme, which applies twodimensional static features, has severely degraded performance in a time-varying communication environment [9]. In addition, the independent design of static features extraction and clustering will increase the complexity of security authentication.…”