4.1 Article

IoT Nodes Authentication and ID Spoofing Detection Based on Joint Use of Physical Layer Security and Machine Learning

Journal

FUTURE INTERNET
Volume 14, Issue 2, Pages -

Publisher

MDPI
DOI: 10.3390/fi14020061

Keywords

physical layer security; wireless fingerprinting; machine learning; intrusion detection

Funding

  1. European Telecommunication Standard Institute (ETSI) technical committee (TC) on Smart Body Area Network (SmartBAN)
  2. European Union's Horizon 2020 Research and Innovation Program [872752]

Ask authors/readers for more resources

This paper discusses the use of physical layer security in future wireless systems as a means of communication security, with a focus on node authentication and spoofing detection in wireless sensor networks. Through machine learning and wireless fingerprinting, nodes can be effectively classified and verified for identity, improving the security performance of the system.
The wide variety of services and applications that shall be supported by future wireless systems will lead to a high amount of sensitive data exchanged via radio, thus introducing a significant challenge for security. Moreover, in new networking paradigms, such as the Internet of Things, traditional methods of security may be difficult to implement due to the radical change of requirements and constraints. In such contexts, physical layer security is a promising additional means to realize communication security with low complexity. In particular, this paper focuses on node authentication and spoofing detection in an actual wireless sensor network (WSN), where multiple nodes communicate with a sink node. Nodes are in fixed positions, but the communication channels varies due to the scatterers' movement. In the proposed security framework, the sink node is able to perform a continuous authentication of nodes during communication based on wireless fingerprinting. In particular, a machine learning approach is used for authorized nodes classification by means of the identification of specific attributes of their wireless channel. Then classification results are compared with the node ID in order to detect if the message has been generated by a node other than its claimed source. Finally, in order to increase the spoofing detection performance in small networks, the use of low-complexity sentinel nodes is proposed here. Results show the good performance of the proposed method that is suitable for actual implementation in a WSN.

Authors

I am an author on this paper
Click your name to claim this paper and add it to your profile.

Reviews

Primary Rating

4.1
Not enough ratings

Secondary Ratings

Novelty
-
Significance
-
Scientific rigor
-
Rate this paper

Recommended

No Data Available
No Data Available