Radio frequency fingerprinting techniques for device identification: a survey

Abbas, Sohail; Abu Talib, Manar; Nasir, Qassim; Idhis, Sally; Alaboudi, Mariam; Mohamed, Ali

doi:10.1007/s10207-023-00801-z

Cited by 2 publications

(3 citation statements)

References 179 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Radio frequency fingerprinting is a technique for the identification and authentication of wireless devices, which has received increased attention from the research community in recent years. As described in [1], the security of wireless networks is a very important aspect to ensure the trust of wireless services, which are now pervasive in our society. In this context, networking and security protocols assume that the identities of users and devices are distinct and unique, but this can be violated by cybersecurity attackers, who can spoof the identity of a wireless device.…”

Section: Introductionmentioning

confidence: 99%

“…On the other side, the deployment of cryptographic frameworks can be costly because of the need to implement processes like key distribution and key management, which can be particularly cumbersome in Internet of Things (IoT) systems like the LoRa devices considered in this study because of the computing limitations of such devices [2]. Recently, RFF has been proposed by various researchers as an alternative or complementary means of cryptographic identification for wireless communications [1,3,4].…”

Section: Introductionmentioning

confidence: 99%

“…The advantage of RFF in comparison to cryptographic techniques is that it does not require the distribution and secure storing of cryptographic materials (which is particularly beneficial for IoT environments) and that it is based on the unique physical properties of the wireless device [3]. On the other side, the identification is based on probability derived from the matching of the fingerprints, and research is still progressing in improving such probability in terms of accuracy and required computing time [1,4], which is also the objective of this study.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

LoRa Radio Frequency Fingerprinting with Residual of Variational Mode Decomposition and Hybrid Machine-Learning/Deep-Learning Optimization

Baldini,

Bonavitacola

2024

Electronics

View full text Add to dashboard Cite

RFF refers to the technique for identifying and classifying wireless devices on the basis of their physical characteristics, which appear in the digital signal transmitted in space. Small differences in the radio frequency front-end of the wireless devices are generated across the same wireless device model during the implementation and manufacturing process. These differences create small variations in the transmitted signal, even if the wireless device is still compliant with the wireless standard. By using data analysis and machine-learning algorithms, it is possible to classify different electronic devices on the basis of these variations. This technique has been well proven in the literature, but research is continuing to improve the classification performance, robustness to noise, and computing efficiency. Recently, DL has been applied to RFF with considerable success. In particular, the combination of time-frequency representations and CNN has been particularly effective, but this comes at a great computational cost because of the size of the time-frequency representation and the computing time of CNN. This problem is particularly challenging for wireless standards, where the data to be analyzed is extensive (e.g., long preambles) as in the case of the LoRa (Long Range) wireless standard. This paper proposes a novel approach where two pre-processing steps are adopted to (1) improve the classification performance and (2) to decrease the computing time. The steps are based on the application of VMD where (in opposition to the known literature) the residual of the VMD application is used instead of the extracted modes. The concept is to remove the modes, which are common among the LoRa devices, and keep with the residuals the unique intrinsic features, which are related to the fingerprints. Then, the spectrogram is applied to the residual component. Even after this step, the computing complexity of applying CNN to the spectrogram is high. This paper proposes a novel step where only segments of the spectrogram are used as input to CNN. The segments are selected using a machine-learning approach applied to the features extracted from the spectrogram using the LBP. The approach is applied to a recent LoRa radio frequency fingerprinting public data set, where it is shown to significantly outperform the baseline approach based on the full use of the spectrogram of the original signal in terms of both classification performance and computing complexity.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

LoRa Radio Frequency Fingerprinting with Residual of Variational Mode Decomposition and Hybrid Machine-Learning/Deep-Learning Optimization

Baldini,

Bonavitacola

2024

Electronics

View full text Add to dashboard Cite

show abstract

Identification of IoT Devices Based on Hardware and Software Fingerprint Features

Jiang,

Dou,

2024

Symmetry

View full text Add to dashboard Cite

Unauthenticated device access to a network presents substantial security risks. To address the challenges of access and identification for a vast number of devices with diverse functions in the era of the Internet of things (IoT), we propose an IoT device identification method based on hardware and software fingerprint features. This approach aims to achieve comprehensive “hardware–software–user” authentication. First, by extracting multimodal hardware fingerprint elements, we achieve identity authentication at the device hardware level. The time-domain and frequency-domain features of the device’s transient signals are extracted and further learned by a feature learning network to generate device-related time-domain and frequency-domain feature representations. These feature representations are fused using a splicing operation, and the fused features are input into the classifier to identify the device’s hardware attribute information. Next, based on the interaction traffic, behavioral information modeling and sequence information modeling are performed to extract the behavioral fingerprint elements of the device, achieving authentication at the software level. Experimental results demonstrate that the method proposed in this paper exhibits a high detection efficacy, achieving 99% accuracy in both software and hardware level identification.

show abstract

Radio frequency fingerprinting techniques for device identification: a survey

Cited by 2 publications

References 179 publications

LoRa Radio Frequency Fingerprinting with Residual of Variational Mode Decomposition and Hybrid Machine-Learning/Deep-Learning Optimization

LoRa Radio Frequency Fingerprinting with Residual of Variational Mode Decomposition and Hybrid Machine-Learning/Deep-Learning Optimization

Identification of IoT Devices Based on Hardware and Software Fingerprint Features

Contact Info

Product

Resources

About