Groundwork for Neural Network-Based Specific Emitter Identification Authentication for IoT

Abstract

Trust is a prominent concern with the continued expansion of the Internet of Things (IoT). As new devices enter the market, device security must be a design pillar. In order to trust these devices, they must be identifiable and authenticated before they begin transmitting possible sensitive information, and given the vast number of IoT devices in the future, it may prove difficult to properly trust and authenticate these authorized devices on networks with current methods. Machine learning neural networks (NNs) have the ability to uniquely identify transmitters based on their physical waveform characteristics which could be used to identify and authenticate IoT nodes in large networks with little impact to latency, providing an extra layer of security and trust. This paper presents the groundwork for performing NN-based specific emitter identification (SEI) on resource constrained IoT devices using only raw in-phase and quadrature (IQ) streams, with protocols to secure IoT networks. As proof of concept, an existing NN-based SEI algorithm is executed on both a resource-rich and a more resource-constrained device with low latency, demonstrating the feasibility of using such algorithms on IoT devices now and in the future.