RF fingerprinting is an emerging technology for identifying hardware-specific features of wireless transmitters and may find important applications in wireless security. In this study, the authors present a new RF fingerprinting scheme using deep neural networks. In particular, a long short-term memory based recurrent neural network is proposed and used for automatically identifying hardware-specific features and classifying transmitters. Experimental studies using identical RF transmitters showed very high detection accuracy in the presence of strong noise (signal-to-noise ratio as low as −12 dB) and demonstrated the effectiveness of the proposed scheme.

This paper presents a compact 213 GHz fundamental oscillator with an optimal embedding network that maximizes the output power. Fabricated in 65-nm bulk CMOS, the oscillator occupies a core area of only 70×40 pm2, owing to the use of a compact low-loss capacitive transformer structure. The oscillator achieves 0.56-mW output power while consuming a DC current of 14.35 mA from a 1-V power supply, representing a recording-breaking DC-to-RF efficiency of 3.9% amongst fundamental oscillators above 200 GHz.