Radio Transmitter Fingerprinting: A Steady State Frequency Domain Approach

We present a novel technique for radio transmitter identification based on frequency domain characteristics. Our technique detects the unique features imbued in a signal as it passes through a transmit chain. We are the first to propose the use of discriminatory classifiers based on steady state spectral features. In laboratory experiments, we achieve 97% accuracy at 30dB SNR and 66% accuracy at 0dB SNR based on eight identicalUniversal Software Radio Peripherals (USRP) transmitters. Our technique can be implemented using today's low cost high-volume receivers and requires no manual performance tuning.