The UTC Graduate School is pleased to announce that Awab Mohammed will present Master's research titled, Investigations into the Role of Entropy-Selected RF-DNA Fingerprint Features on ID-verification Performance in the Presence of Rogue Emitters on 12/04/2023 at 3:00 PM in EMCS Maytag Conference Room. Everyone is invited to attend. 

Engineering

Chair: Donald R. Reising

Co-Chair: 

Abstract:
The projected deployment of Internet of Things (IoT) devices is anticipated to reach 30.9 billion by 2025, marking an impressive growth of 572% within a ten year span of time. Most IoT devices lack sufficient security measures to counter the escalating threats from more sophisticated adversaries. Consequently, prioritizing IoT security becomes imperative, necessitating the development of robust security protocols. One such security approach is Specific Emitter Identification (SEI), which uniquely identifies wireless emitters passively through distinctive and inherent features in their transmitted signals. This work integrates entropy-selected Radio Frequency-Distinct Native Attributes (RF-DNA) fingerprinting, a specialized form of SEI, with Deep Learning (DL) techniques to authenticate the identity of authorized emitters. This authentication becomes crucial in the presence of ’rogue’ emitters who deliberately impersonate authorized emitters using falsified digital credentials. Using entropy-ranked regions within the Time-Frequency (TF) representations of an emitter’s signals. RF-DNA fingerprints are extracted from these entropy-selected regions, and the obtained results demonstrate the success of a Convolutional Neural Network (CNN) in verifying the identities of all authorized emitters at an accuracy rate of 95% or higher. Additionally, the CNN effectively detects and rejects all twelve rogue attacks with an accuracy rate of 89% or better, at a Signal-to-Noise Ratio (SNR) of 9 dB.