Radio frequency (RF) fingerprinting authenticates wireless devices from hardware-induced I/Q impairments, typically with deep learning feature extractors that are accurate but opaque, limiting their use in security critical settings. We propose Polar Monotonic Kolmogorov-Arnold Networks (Polar MKAN), a block partitioned monotonic encoder on polar inputs in which each latent dimension depends exclusively on magnitude or phase, yielding channel separation and monotone responses by construction.
The paper presents a calibrated radio‑frequency fingerprinting approach that handles co‑channel interference from multiple transmitters. By framing the task as a multi‑label classification problem, the authors use a 1D CNN and calibrate confidence thresholds to bound the average number of false negatives, ensuring reliable detection of spectrum violations. Experiments on the POWDER 5G testbed with Wi‑Fi, LTE, and 5G NR signals achieve up to 97% accuracy, with calibrated recall closely matching the specified false‑negative bounds even under out‑of‑distribution interference.
By Tariq Abdul-Quddoos, Xiangfang Li, Lijun Qian
arXiv:2507.12133v2 Announce Type: replace
Abstract: Device recognition is vital for security in wireless communication systems, particularly for applications like access control. Radio Frequency Fing...
By Hanwen Liu, Yuhe Huang, Yifeng Gong, Yanjie Zhai, Jiaxuan Lu
The paper introduces FreqSpaNet, a neural network designed to detect hardware integrity violations in wireless devices by learning spatio-frequency polarization fingerprints (SFPFs). It employs a dual-branch architecture: a frequency branch that captures local variations across neighboring frequencies and a geometry-aware spatial branch that models directional relationships using angular information. The two learned representations are adaptively fused, and complementary pretraining is used to preserve distinct characteristics while capturing shared information, achieving a mean AUROC of 96.31%—9.05 points above the baseline—across seven hardware replacement scenarios.
By Xiaoxuan Huang, Jinlong Xu, YiZhe Wang, Meng Zhang, Xian Li, Yuying Bian
The paper presents a channel-informed neural network for physical-layer key generation (PKG) that extracts binary key features directly from IQ measurements while grounding the representation in the multipath channel. The multi-task recurrent network jointly learns reciprocity-preserving features and an auxiliary channel estimate, using deep metric learning and channel-informed supervision. Experiments on indoor and outdoor software-defined-radio data show lower bit disagreement for legitimate users, improved key diversity with ray-traced augmentation, and successful NIST randomness tests after SHA-3 privacy amplification.
By Jose Angel Sanchez Viloria, George Sklivanitis, Dimitris Pados, Elizabeth Serena Bentley
arXiv:2608. 08439v1 Announce Type: cross Abstract: Heterogeneous RF sensing differs substantially in feature structure, spatial layout, and temporal scale, making existing models difficult to reuse across devices, environments, and RF modalities.
By Jing Wang, Zhu Wang, Changlong Cheng, Yifan Guo, Yin Zhang