Explainable and Hardware-Efficient Jamming Detection for 5G Networks Using the Convolutional Tsetlin Machine

Vojtech Halenka; Mohammadreza Amini; Per-Arne Andersen; Ole-Christoffer Granmo; Burak Kantarci

eess.SPMar 7, 2026

Explainable and Hardware-Efficient Jamming Detection for 5G Networks Using the Convolutional Tsetlin Machine

Authors: Vojtech Halenka, Mohammadreza Amini, Per-Arne Andersen, Ole-Christoffer Granmo, Burak Kantarci

Organizations: Center of Artificial Intelligence Research, University of Agder, Grimstad, Norway · School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada

Abstract

All applications in fifth-generation (5G) networks rely on stable radio-frequency (RF) environments to support mission-critical services in mobility, automation, and connected intelligence. Their exposure to intentional interference or low-power jamming threatens availability and reliability, especially when such attacks remain below link-layer observability. This paper investigates lightweight, explainable, and hardware-efficient jamming detection using the Convolutional Tsetlin Machine (CTM) operating directly on 5G Synchronization Signal Block (SSB) features. CTM formulates Boolean logic clauses over quantized inputs, enabling bit-level inference and deterministic deployment on FPGA fabrics. These properties make CTM well suited for real-time, resource-constrained edge environments anticipated in 5G. The proposed approach is experimentally validated on a real 5G testbed using over-the-air SSB data, emulating practical downlink conditions. We benchmark CTM against a convolutional neural network (CNN) baseline under identical preprocessing and training pipelines. On the real dataset, CTM achieves comparable detection performance (Accuracy 91.53 +/- 1.01 vs. 96.83 +/- 1.19 for CNN) while training $9.5\times$ faster and requiring 14x less memory (45~~MB vs.\ 624~~MB). Furthermore, we outline a compact FPGA-oriented design for Zybo~Z7 (Zynq-7000) and provide resource projections (not measured) under three deployment profiles optimized for latency, power, and accuracy trade-offs. The results show that the CTM provides a practical, interpretable, and resource-efficient alternative to conventional DNNs for RF-domain jamming detection, establishing it as a strong candidate for edge-deployed, low-latency, and security-critical 5G applications while laying the groundwork for B5G systems.

Figures & tables

Parameter	Value
Carrier Frequency ( $f_{c}$ )	632 MHz
Bandwidth	35 MHz
Sampling Rate	15.625 MHz
Antenna Type	Wideband omnidirectional
Duration per Capture	200 ms
FFT Size	1024

TABLE I: Setup and acquisition parameters for data collection.

Preprocessing	Accuracy	s	T	patch	max_lit
Enhanced Otsu	91.53 ± 1.01	2.08	477	10×10	22
Paper Original	91.47 ± 1.06	3.64	326	10×10	28
Multi Level	90.88 ± 1.09	1.06	721	7×7	50
Adaptive Thresh	80.20 ± 1.64	1.78	192	9×9	30
CNN	96.83 ± 1.19	–	–	–	–

TABLE II: Preprocessing methods: 5-fold cross-validation accuracy with CTM best found parameters

Model	Acc. [%]	Train. Time [s]	Infer. Time [s]	Mem. [MB]
CTM	91.96	44.4	2.5	45.2
CNN	96.81	3205.4	0.8	892.1

TABLE III: Accuracy and complexity metrics of CTM vs CNN

Metric	TM	CNN
Training Time (s)	321.69	3107.91
Inference Throughput (samples/s)	46.23	78.23
Model Memory Usage (MB)	45.06	623.69

TABLE IV: CTM (incl. preprocessing) vs. CNN .

Fig. 3: Contributions of individual pixels, Red - Jamming, Blue - Pure, according to the trained CTM , using literal mentions count

Fig. 4: Contributions of individual pixels, Red - Jamming, Blue - Pure, according to the trained CNN , using GradCAM

Profile	Clauses	LUT s	Samples/s
Power	256	$\sim$ 7.7k–15.4k	$\sim$ 1.0–2.5k
Latency	512	$\sim$ 15k–31k	$\sim$ 2.0–4.6k
Accuracy	800	$\sim$ 24k–48k	$\sim$ 1.1–2.5k

TABLE V: Projected CTM inference footprints on Z7 . LUT s use a 30–60/clause envelope, 100 MHz, stride = 1, and 80 % efficiency. No new measurements; literature-based projection only.

Wireless Communications

Wireless communications studies how information is sent over radio links and how networks manage signals, spectrum, and resources reliably.

See all 400 papers

Toward Resilient 5G Networks: Comparative Analysis of Federated and Centralized Learning for RF Jamming Detection
May 3, 2026Samhita Kuili, Mohammadreza Amini, Burak KantarciWireless Communications Privacy-Preserving ML
School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada
O-RAN-Native Jamming Detection Under Network Heterogeneity
Oct 14, 2026Sneihil Gopal, Fernando J. Cintrón, Richard A. RouilWireless Communications Anomaly Detection
PREP Associate, National Institute of Standards and Technology (NIST), USA · Department of Physics, Georgetown University, USA · National Institute of Standards and Technology (NIST), USA
Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems
Mar 3, 2026Mengru Wu, Jiawei Li, Jiaqi Wei +3Distributed Inference Edge Computing
College of Information Engineering, Zhejiang University of Technology, Hangzhou 310023, China · School of Communications and Information Engineering, Nanjing University of Posts and Telecommunications, Nanjing 210003, China · Department of Electronic and Electrical Engineering, University College London, WC1E 7JE London, U.K. +2

May 3, 2026J/K move · Enter open · S save

Toward Resilient 5G Networks: Comparative Analysis of Federated and Centralized Learning for RF Jamming Detection

Samhita Kuili, Mohammadreza Amini, Burak Kantarci

School of Electrical Engineering and Computer Science, University of Ottawa, Ottawa, ON, Canada

Wireless Communications Privacy-Preserving ML Federated Learning

Open paper AskPDF arXiv

Jamming attacks are proliferating and pose a significant threat to the security of 5G and beyond networks. These attacks target 5G radio frequency (RF) domain and can disrupt the communication in wireless networks. While conventional machine learning and deep learning approaches demonstrate its potential for jamming detection, they typically require centralized data collection, compromising the privacy of user equipment (UEs). This work proposes a federated learning (FL)-based jamming detection framework that operates on over-the-air In-phase and Quadrature (IQ) samples extracted from Synchronization Signal Blocks (SSBs) in the RF domain. The framework enables collaborative model training across multiple UEs without sharing raw RF signal data. We adopt Federated Averaging (FedAvg) algorithm to train a 1D convolutional neural network (1DCNN) for effective detection of attacks. Numerical results demonstrate that the proposed FL framework achieves 97% accuracy and 97% F1-score, outperforming centralized baselines including MLP, 1DCNN, SVM, and logistic regression, while preserving the data privacy of all participating UEs

Abstract

Wireless Communications

Explore similar work

Toward Resilient 5G Networks: Comparative Analysis of Federated and Centralized Learning for RF Jamming Detection

O-RAN-Native Jamming Detection Under Network Heterogeneity

Joint Optimization of Model Partitioning and Resource Allocation for Anti-Jamming Collaborative Inference Systems