Ncil (EPSRC). EPSRC-LWEC Challenge Fellowship EP/N02950X/1. BI-0115 Biological Activity Institutional Critique Board Statement: Not applicable. Informed Consent Statement: Not applicable. Information Availability Statement: Data have already been published and access is obtainable at https://doi.org/ 10.25919/131d-sj06. Acknowledgments: Tom Walsh, Suzanne Metcalfe, and Jason Wylie are thanked for their technical help. Conflicts of Interest: The authors declare no conflict of interest.
applied sciencesArticleRadio Frequency Fingerprinting for Frequency Hopping Emitter IdentificationJusung Kang 1 , Younghak Shin two , Hyunku Lee 3 , Jintae Park four and Heungno Lee 1, 3School of Electrical Engineering and Computer system Science, Gwangju Institute of Science and Technology, Gwangju 61005, Korea; [email protected] Department of Laptop or computer Engineering, Mokpo National University, Muan-gun 58554, Korea; [email protected] LIG Nex1 Enterprise Ltd., Yongin 16911, Korea; [email protected] Agency for Defense Improvement, Betamethasone disodium medchemexpress Daejeon 34063, Korea; [email protected] Correspondence: [email protected]; Tel.: 82-62-715-Citation: Kang, J.; Shin, Y.; Lee, H.; Park, J.; Lee, H. Radio Frequency Fingerprinting for Frequency Hopping Emitter Identification. Appl. Sci. 2021, 11, 10812. https://doi.org/ 10.3390/app112210812 Academic Editor: Ernesto Limiti Received: eight October 2021 Accepted: 11 November 2021 Published: 16 NovemberAbstract: In a frequency hopping spread spectrum (FHSS) network, the hopping pattern plays a crucial part in user authentication at the physical layer. On the other hand, lately, it has been attainable to trace the hopping pattern through a blind estimation process for frequency hopping (FH) signals. In the event the hopping pattern is often reproduced, the attacker can imitate the FH signal and send the fake data to the FHSS method. To stop this scenario, a non-replicable authentication method that targets the physical layer of an FHSS network is necessary. Within this study, a radio frequency fingerprintingbased emitter identification system targeting FH signals was proposed. A signal fingerprint (SF) was extracted and transformed into a spectrogram representing the time requency behavior of your SF. This spectrogram was trained on a deep inception network-based classifier, and an ensemble method using the multimodality with the SFs was applied. A detection algorithm was applied for the output vectors from the ensemble classifier for attacker detection. The outcomes showed that the SF spectrogram is usually successfully utilized to recognize the emitter with 97 accuracy, as well as the output vectors in the classifier is usually effectively utilized to detect the attacker with an area under the receiver operating characteristic curve of 0.99. Key phrases: frequency hopping signals; radio frequency fingerprinting; emitter identification; outlier detection; physical layer safety; inception block; deep finding out classifier1. Introduction By far the most critical process in user authentication of a wireless communication program is to identify the emitter info of RF signals. A common strategy to confirm the emitter facts, that is certainly, the emitter ID, is always to decode the address field of your medium access control (MAC) frame [1]. Nonetheless, beneath this digitized information-based authentication process on a MAC layer, an attacker can possess the address details and imitate it as an authenticated user. To stop this weakness, a physical layer authentication course of action, namely radio frequency (RF) fingerprinting, has been studied in recent years.