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. On a synthetic gain and carrier frequency offset (CFO) benchmark, Polar MKAN reaches 57.2 percent DCI Disentanglement versus at most 12.9 percent for unpartitioned baselines. We further evaluate the detection accuracy trade off on real data and the sensitivity to blind CFO compensation.
Figures & tables
Fig. 1 : Self-supervised UED workflow.
Fig. 2 : Polar MKAN. (a) Exclusive connections, where Fϕ1,Fϕ2 receive only phase inputs and FR only magnitude inputs. (b) Idealised feature-space geometry away from the phase branch cut.
Train
Evaluation
Devices
1000
100
Bursts/device
1
1
Burst length ( N )
256
256
Samples/symbol ( L )
4
4
SNR range (dB)
[10,30]
[10,30]
TABLE I : Composition of the synthetic dataset enabling a controlled disentanglement study.
Architecture
D
C
CNN
6.1±4.2
6.7±3.4
KAN
10.0±4.7
9.8±4.0
MKAN
7.4±3.1
9.5±2.9
Polar CNN
5.0±2.4
5.3±1.8
Polar KAN
12.9±4.8
13.1±4.9
Polar MKAN
57.2±6.0
47.0±4.0
TABLE II : DCI Disentanglement (D) and Completeness (C) (%, mean ± 95% CI over 10 runs).
Fig. 3 : Sign consistency of the phase features vs. fraction of samples whose phase wraps (95% CI, 10 runs).
Fig. 5 : Response to a positive carrier-phase rotation on WiSig ManyTx.
Synthetic
SingleDay
ManyTx
FE
AUC
F1
AUC comp
AUC
F1
AUC comp
AUC
F1
AUC comp
CNN
62.1 ± 2.2
24.8 ± 3.6
51.1 ± 1.7
71.0 ± 2.5
36.8 ± 5.4
66.8 ± 2.4
64.7 ± 1.8
28.8 ± 3.9
62.3 ± 1.3
KAN
78.4 ± 4.2
62.9 ± 8.7
51.1 ± 1.1
89.8 ± 3.6
74.0 ± 7.0
76.2 ± 4.6
73.2 ± 2.6
44.0 ± 5.5
67.1 ± 3.1
MKAN
74.4 ± 4.6
53.3 ± 8.2
49.8 ± 1.4
79.7 ± 5.8
61.3 ± 7.9
66.5 ± 5.1
69.9 ± 1.2
38.2 ± 2.4
60.8 ± 2.3
Polar CNN
53.6 ± 1.6
20.6 ± 2.2
50.4 ± 0.9
64.8 ± 2.9
27.4 ± 5.9
62.6 ± 2.9
61.7 ± 1.1
24.1 ± 2.0
60.9 ± 1.0
Polar KAN
56.3 ± 5.3
23.2 ± 7.5
50.5 ± 1.7
82.8 ± 4.6
59.8 ± 7.1
71.0 ± 5.8
66.3 ± 1.8
30.9 ± 4.0
62.2 ± 2.4
TABLE III : UED results (%). AUC and F1 uncompensated, AUC comp with blind CFO compensation before training and evaluation. Std over 10 seeds (synthetic) or device folds (WiSig). Best uncompensated in bold.
Radio-frequency (RF) fingerprinting systems must operate in open-world environments where signals from unknown transmitters and temporal drift introduce distribution shift at test time. Out-of-distribution (OOD) detection provides a natural framework for this problem, yet its application to RF fingerprinting (RFF) remains limited. A key barrier to their adoption is that most OOD detectors require auxiliary OOD data for parameter tuning, an assumption that is difficult to satisfy in RF environments where representative OOD data is impractical to collect. In this work, we introduce a promising set of OOD detection methods from the machine learning literature to open-set RFF domain. We present these methods within a unified mathematical framework based on information theory, which is a natural framework for communication systems. Our framework allows for the systematic analysis of methods and development of new methods. We further demonstrate the applicability of recent work on tuning OOD detectors without given OOD tuning data for open-set RFF. We evaluate on the POWDER RF fingerprinting dataset, showing that detectors tuned without any given OOD data achieve performance comparable to baselines with access to true OOD tuning data and greatly out-perform baseline approaches without access to true OOD tuning data, showcasing the practical viability for the RFF problem.
Radio frequency fingerprint identification (RFFI) exploits transmitter-specific hardware imperfections as physicallayer identity cues for Internet of Things (IoT) devices, but deep models often degrade across acquisition environments. In multi-antenna reception, antenna topology and frequencyoffset dynamics structure receiver observations, while capturedependent variation distorts target embeddings and misaligns source-trained decision boundaries. This article proposes physicsinformed structure anchoring with capture-aware prototype calibration (PISA-CAPC) to address both representation and decision mismatches. The two stages separate source representation construction from target decision correction. During source training, PISA organizes antenna tokens through a topology-guided graph, conditions propagation on CFO-derived acquisition dynamics, and applies bounded contextual residual suppression to preserve identity evidence. At deployment, unlabeled capture-aware prototype calibration (U-CAPC) estimates capture-local prototypes and recalibrates target decision scores while keeping the representation and source classifier fixed. Thus, calibration uses neither target labels nor target-domain backbone updates. On a measured WiFi benchmark with four receive antennas and ten transmitters, PISA-CAPC achieves a mean target-domain Macro-F1 of 0.9257 under a balanced transductive setting. Component ablations support complementary roles for topology-guided anchoring, CFO-conditioned modulation, reliability-aware token aggregation, contextual suppression, and capture-aware calibration. These results indicate that physically motivated representation learning can be combined with labelfree decision calibration to improve cross-environment RFFI under the evaluated protocol without changing the deployed backbone.
Fengchong Yao, Jianbing Li, Qing Liu +4
School of Information Systems Engineering, Information Engineering University, Zhengzhou 450001, China.
Radio Frequency(RF)-Fingerprinting is a spectrum monitoring technique that identifies specific transmitters based on hardware impairments imprinted within the emitted signal. Although widely researched, studies almost exclusively consider scenarios where only one transmitter is emitting at a time, limiting real world applicability. In this work, we further the study of RF-Fingerprinting by considering co-channel interference, with multiple emitted signals interfering with each other, overlapping in time and frequency. Specifically, we formulate this problem as a multi-label classification problem and employ a 1D convolutional neural network (CNN). Furthermore, the models are calibrated such that the confidence thresholds for the label probabilities are derived, with guarantees on the upper bound on the average number of False Negatives, providing a degree of confidence in not missing a true spectrum policy violation. The proposed method is validated using real world data from the POWDER 5G testbed on devices transmitting 802.11a(Wi-Fi), 4G LTE, and 5G NR waveforms. The results show accuracy as high as 97% and as low as 73% after calibration depending on channel conditions. Also calibrating for various average false negatives upper bounds achieves micro recall scores of approximately (1 - calibrated false negatives) with the calibration robust to out-of-distribution interference, demonstrating the potential of the proposed method in a realistic high contention wireless environment
Tariq Abdul-Quddoos, Xiangfang Li, Lijun Qian
CREDIT Center and Department of Electrical and Computer Engineering Prairie View A&M University, Texas A&M University System Prairie View, TX 77446, USA