Specific Emitter Identification (SEI) is the association of a received signal to a unique emitter, and is made possible by the naturally occurring and unintentional characteristics an emitter imparts onto each transmission, known as its radio frequency fingerprint. This work presents an approach for identifying emitters using Convolutional Neural Networks (CNNs) to estimate the Inphase/Quadrature (IQ) imbalance parameters of each emitter, using only the recieved raw IQ data as input. Because an emitter’s IQ imbalance parameters will not change as it changes modulation schemes, the proposed approach has the ability to track emitters, even as they change modulation scheme. The performance of the developed approach is evaluated using simulated quadrature amplitude modulation (QAM) and phase-shift keying (PSK) signals, and the impact of signal-to-noise ratio (SNR), imbalance value, and modulation scheme are considered. Further, the developed approach is shown to outperform a comparable feature-based approach, while making fewer assumptions and using less data per decision.
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 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 neural network-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 neural network-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.
Specific Emitter Identification (SEI) is the act of matching a received signal to an emitter using a database of radio frequency (RF) features belonging to known transmitters. SEI systems are of vital importance to the military for applications such as early warning systems, emitter tracking, and emitter location, and, more recently, have been used in cognitive radio systems to enforce Dynamic Spectrum Access (DSA) rules [1], [2]. This work investigates using Convolutional Neural Networks (CNNs) as feature learners and extractors, paired with the clustering algorithm DBSCAN, to perform SEI. The process through which emitter-specific features are extracted from raw I/Q data streams is described in detail, including the CNN architecture, design, and training. Extensive performance analysis demonstrates the effectiveness of the proposed approach in identifying emitters, and shows that features extracted from CNNs can be used to differentiate between devices unseen in training.
Transfer learning is a pervasive technology in computer vision and natural language processing fields, yielding exponential performance improvements by leveraging prior knowledge gained from data with different distributions. However, while recent works seek to mature machine learning and deep learning techniques in applications related to wireless communications, a field loosely termed radio frequency machine learning, few have demonstrated the use of transfer learning techniques for yielding performance gains, improved generalization, or to address concerns of training data costs. With modifications to existing transfer learning taxonomies constructed to support transfer learning in other modalities, this paper presents a tailored taxonomy for radio frequency applications, yielding a consistent framework that can be used to compare and contrast existing and future works. This work offers such a taxonomy, discusses the small body of existing works in transfer learning for radio frequency machine learning, and outlines directions where future research is needed to mature the field.
20 September 2021 in IEEE Open Journal of the Communications Society
While deep learning (DL) technologies are now pervasive in state-of-the-art Computer Vision (CV) and Natural Language Processing (NLP) applications, only in recent years have these technologies started to sufficiently mature in applications related to wireless communications, a field loosely termed Radio Frequency Machine Learning (RFML). In particular, recent research has shown DL to be an enabling technology for Cognitive Radio (CR) applications as well as a useful tool for supplementing expertly defined algorithms for spectrum awareness applications such as signal detection, estimation, and classification. A major driver for the usage of RFML is that little, to no, a priori knowledge of the intended spectral environment is required, given that there is an abundance of representative raw Radio Frequency (RF) data to facilitate training and evaluation. However, in addition to this fundamental need for sufficient data, there are other key considerations, such as trust, security, and hardware requirements, that must be taken into account before deploying RFML systems in real-world wireless communication applications that largely go unaddressed in the current literature. This paper examines the prior works related to these major research considerations, with focus on the dependencies between them and factors unique to the RFML space.
Generating high-quality, real-world, well-labeled datasets for radio frequency machine learning (RFML) applications often proves prohibitively cumbersome and expensive, leading to the lowavailability of high-fidelity, low-cost datasets. Specific emitter identification (SEI) in particular requires a hardware setup capable of supporting transmitting using many different radios, while automated modulation classification (AMC) performance is primarily driven by SNR, channel effects, and the similarity of modulation types. These factors give rise to the need for scalable methods of inexpensive dataset generation. This paper describes the design considerations and a proof-of-concept implementation of a blind user reconfigurable platform capable of creating SEI and AMC datasets throughout a variety of real-world conditions. This paper additionally describes the reliability and performance of the platform relative to existing real-world data generation methods and compares generated datasets to those already present in the literature. This work also describes the software post-processing steps taken to isolate, label, and cull captured data and transform these into a high-quality dataset.