Improved RF Fingerprint-based Identity Verification in the Presence of an SEI Mimicking Adversary

Specific Emitter Identification (SEI) is advantageous for its ability to passively identify emitters by exploiting distinct, unique, and organic features unintentionally imparted upon every signal during formation and transmission. These features are attributed to the slight variations and imperfections in the Radio Frequency (RF) front end; thus, SEI is being proposed as a physical layer security technique. Most SEI work assumes the targeted emitter is a passive source with immutable and difficult-to-mimic signal features. However, Software-Defined Radio (SDR) proliferation and Deep Learning (DL) advancements require a reassessment of these assumptions because DL can learn SEI features directly from an emitter’s signals, and SDR enables signal manipulation. This paper investigates a strong adversary that uses SDR and DL to mimic an authorized emitter’s signal features to circumvent SEI-based identity verification. The investigation considers three SEI mimicry approaches, two different SDR platforms, the application of matched filtering before SEI feature extraction, and selecting the most informative portions of the signals’ time-frequency representation using entropy. The results show that “off-the-shelf” DL achieves effective SEI mimicry. Additionally, SDR constraints impact SEI mimicry effectiveness and suggest an adversary’s minimum requirements. Our results show matched filtering results in the identity of all authorized emitters being correctly verified at a rate of 90% or higher, the rejection of all other authorized emitters–whose IDs are not being verified–at a rate of 97% or higher, and rejection of forty-five out of forty-eight SEI mimicry attacks. Based on the results presented herein, future SEI research must consider adversaries capable of mimicking another emitter’s SEI features or manipulating their own.