RF Fingerprinting Unmanned Aerial Vehicles With Non-Standard Transmitter Waveforms

Soltani, Nasim; Reus-Muns, Guillem; Salehi, Batool; Dy, Jennifer G.; Ioannidis, Stratis; Chowdhury, Kaushik R.

doi:10.1109/tvt.2020.3042128

Cited by 65 publications

(22 citation statements)

References 28 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The rogue devices will be classified as one of the legitimate devices which is unacceptable. To this end, the authors in [17], [26], [36], [46] have proposed several rogue device detection schemes. However, some require more than one neural networks to be deployed, and none of them is scalable when a new legitimate device joins the system.…”

Section: Related Workmentioning

confidence: 99%

Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa

Shen

Zhang

Marshall

et al. 2022

IEEE Trans.Inform.Forensic Secur.

141

View full text Add to dashboard Cite

Radio frequency fingerprint identification (RFFI) is a promising device authentication technique based on the transmitter hardware impairments. In this paper, we propose a scalable and robust RFFI framework achieved by deep learning powered radio frequency fingerprint (RFF) extractor. Specifically, we leverage the deep metric learning to train an RFF extractor, which has excellent generalization ability and can extract RFFs from previously unseen devices. Any devices can be enrolled via the pre-trained RFF extractor and the RFF database can be maintained efficiently for allowing devices to join and leave. Wireless channel impacts the RFF extraction and is tackled by exploiting channel independent feature and data augmentation. We carried out extensive experimental evaluation involving 60 commercial off-the-shelf LoRa devices and a USRP N210 software defined radio platform. The results have successfully demonstrated that our framework can achieve excellent generalization abilities for device classification and rogue device detection as well as effective channel mitigation.

show abstract

Section: Related Workmentioning

confidence: 99%

Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa

Shen

Zhang

Marshall

et al. 2022

IEEE Trans.Inform.Forensic Secur.

141

View full text Add to dashboard Cite

show abstract

“…An algorithm for classifying identical UAVs (i.e., same make and model) in hovering flight mode was proposed in [17]. Although an overall accuracy of 91% was achieved, the authors did not consider interference mitigation strategy for other ISM devices operating at 2.4 GHz.…”

Section: Related Workmentioning

confidence: 99%

“…However, the majority of the UAV signals are control signals. The more recent dataset is the hovering UAVs RF fingerprinting dataset [17], where seven identical (i.e., same make and model) UAVs were utilized. However, the only flight mode considered is the hovering mode.…”

Section: Related Workmentioning

confidence: 99%

Hierarchical Learning Framework for UAV Detection and Identification

Medaiyese¹,

Ezuma²,

Lauf³

et al. 2021

Preprint

View full text Add to dashboard Cite

The ubiquity of unmanned aerial vehicles (UAVs) or drones is posing both security and safety risks to the public as UAVs are now used for cybercrimes. To mitigate these risks, it is important to have a system that can detect or identify the presence of an intruding UAV in a restricted environment. In this work, we propose a radio frequency (RF) based UAV detection and identification system by exploiting signals emanating from both the UAV and its flight controller, respectively. While several RF devices (i.e., Bluetooth and WiFi devices) operate in the same frequency band as UAVs, the proposed framework utilizes a semisupervised learning approach for the detection of UAV or UAV's control signals in the presence of other wireless signals such as Bluetooth and WiFi. The semi-supervised learning approach uses stacked denoising autoencoder and local outlier factor algorithms. After the detection of UAV or UAV's control signals, the signal is decomposed by using Hilbert-Huang transform and wavelet packet transform to extract features from the timefrequency-energy domain of the signal. The extracted feature sets are used to train a three-level hierarchical classifier for identifying the type of signals (i.e., UAV or UAV control signal), UAV models, and flight mode of UAV. To demonstrate the feasibility of the proposed framework, we carried out an outdoor experiment for data collection using six UAVs, five Bluetooth devices, and two WiFi devices. The acquired data is called Cardinal RF (CardRF) dataset, and it is available for public use to foster UAV detection and identification research.

show abstract

“…Moreover, the wireless environment is too complex to be modeled accurately, and constraining the choice of the processing blocks to only one of several candidates may lower the performance. On the other hand, Neural Networks (NNs) provide an adaptable and noise-resilient solution for many physical layer processing tasks, such as modulation classification [1] and RF fingerprinting [2], [3], that improve the performance of their traditional counterparts. Similarly, in the domain of receiver design, NNs can offer a closed-form and flexible solution by learning to imitate previous channel estimations, symbol demappings, and decodings, instead of explicitly realizing the mathematical form of these processing blocks.…”

Section: Introductionmentioning

confidence: 99%

Neural Network-based OFDM Receiver for Resource Constrained IoT Devices

Soltani¹,

Cheng²,

Belgiovine³

et al. 2022

Preprint

Self Cite

View full text Add to dashboard Cite

Orthogonal Frequency Division Multiplexing (OFDM)-based waveforms are used for communication links in many current and emerging Internet of Things (IoT) applications, including the latest WiFi standards. For such OFDM-based transceivers, many core physical layer functions related to channel estimation, demapping, and decoding are implemented for specific choices of channel types and modulation schemes, among others. To decouple hard-wired choices from the receiver chain and thereby enhance the flexibility of IoT deployment in many novel scenarios without changing the underlying hardware, we explore a novel, modular Machine Learning (ML)-based receiver chain design. Here, ML blocks replace the individual processing blocks of an OFDM receiver, and we specifically describe this swapping for the legacy channel estimation, symbol demapping, and decoding blocks with Neural Networks (NNs). A unique aspect of this modular design is providing flexible allocation of processing functions to the legacy or ML blocks, allowing them to interchangeably coexist. Furthermore, we study the implementation cost-benefits of the proposed NNs in resource-constrained IoT devices through pruning and quantization, as well as emulation of these compressed NNs within Field Programmable Gate Arrays (FPGAs). Our evaluations demonstrate that the proposed modular NN-based receiver improves bit error rate of the traditional non-ML receiver by averagely 61% and 10% for the simulated and over-the-air datasets, respectively. We further show complexity-performance tradeoffs by presenting computational complexity comparisons between the traditional algorithms and the proposed compressed NNs.

show abstract

RF Fingerprinting Unmanned Aerial Vehicles With Non-Standard Transmitter Waveforms

Cited by 65 publications

References 28 publications

Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa

Towards Scalable and Channel-Robust Radio Frequency Fingerprint Identification for LoRa

Hierarchical Learning Framework for UAV Detection and Identification

Neural Network-based OFDM Receiver for Resource Constrained IoT Devices

Contact Info

Product

Resources

About