Concealing Radio Frequency Fingerprints via Active Adversarial Perturbation

Radio frequency fingerprinting (RFF) is an emerging technology to identify a radio device via recognizing its unique feature that originated from manufacturing imperfections. Nevertheless, these invariant hardware characteristics can be exploited by adversaries, potentially compromising device privacy, even with user anonymity measures in place. This paper addresses the challenge of concealing RF fingerprints in the context of pilot signal-based fingerprint identification. Specifically, artificial perturbations are applied to the radio signal, focusing on the pilot signal during radio transmission. To prevent neural models from recognizing the unique hardware-induced features embedded in the pilot signal, we generate a set of active artificial perturbations through adversarial attack optimization. The perturbed signal aims to mislead the neural models in device identification, thereby obfuscating RF fingerprints and preventing unauthorized identification from potential attackers. To ensure normal communication is unaffected, we theoretically analyze the channel estimation error caused by the perturbation to the pilot signal, and show that the impairments to communication can be controlled within a limited range. To demonstrate effectiveness, we implement the entire fingerprinting and de-fingerprinting process based on a 4G LTE testbed. Extensive experiments demonstrate that the proposed method can effectively conceal the device-specific feature against RF fingerprinting neural models.