International Journal of Communication Systems最新文献

{"title":"Blockchain-Enabled Cross-Device Authentication and Efficient Task Allocation Using Fuzzy Grey Wolf Optimization for IoT Networks","authors":"Vinay Maurya, Vinay Rishiwal, Mano Yadav, Mohammad Shiblee, Udit Agarwal, Ajay Yadav","doi":"10.1002/dac.70632","DOIUrl":"https://doi.org/10.1002/dac.70632","url":null,"abstract":"<div>\u0000 \u0000 <p>Cross-device authentication and task allocation across IoT devices, nodes, sensors, and gateways are difficult due to limited resource constraints and the heterogeneous nature of IoT devices. Traditionally, IoT devices rely on centralized servers, which pose single points of failure, data breaches, and security risks. To overcome these challenges, this paper proposes a framework for cross-device authentication and task allocation in an IoT network. To enable secure, faster cross-device communication, the paper proposed the BCHAuth algorithm, which integrates blockchain and ChaCha20-Poly1305 cryptography. Additionally, for optimal task allocation, FGWO is proposed coupled with fuzzy logic and grey wolf optimization algorithm. Initially, each IoT device is assigned a unique, decentralized ID and transaction records are stored in the blockchain's on-chain metadata via a smart contract. Smart contracts define the registration process and authentication protocols to ensure that only authorized devices with valid credentials can participate in the IoT network. To address the complex task-allocation problem, the proposed FGWO adapts conventional GWO to the discrete and heterogeneous IoT environment. The fuzzy inference system (FIS) evaluates each authenticated and eligible device using its processing power <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>π</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>i</mi>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {pi}_i $$</annotation>\u0000 </semantics></math>, current workload <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>λ</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>i</mi>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {lambda}_i $$</annotation>\u0000 </semantics></math>, available bandwidth <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>β</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>i</mi>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {beta}_i $$</annotation>\u0000 </semantics></math>, residual energy <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <msub>\u0000 <mrow>\u0000 <mi>E</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>i</mi>\u0000 </mrow>\u0000 </msub>\u0000 </mrow>\u0000 <annotation>$$ {E}_i $$","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 17","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149177266","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FPGA Implementation of a 20 Mb/s OOK/8b10b VLC Receiver With Edge-Triggered Oversampled CDR and Measurement-Driven Calibration Characterization","authors":"M. Kerim Taş, M. Selim Demir, V. Emre Levent","doi":"10.1002/dac.70626","DOIUrl":"https://doi.org/10.1002/dac.70626","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper reports an FPGA-based visible light communication (VLC) receiver prototype employing on–off keying (OOK) with 8b/10b line coding at a 20 Mb/s line rate (effective payload <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mo>≈</mo>\u0000 </mrow>\u0000 <annotation>$$ approx $$</annotation>\u0000 </semantics></math> 16 Mb/s). The transmitter and receiver use 100 MHz DAC/ADC devices, yielding an oversampling ratio <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>M</mi>\u0000 <mo>=</mo>\u0000 <mn>5</mn>\u0000 </mrow>\u0000 <annotation>$$ M=5 $$</annotation>\u0000 </semantics></math>. The receiver performs <i>real-time</i> clock and data recovery (CDR) on FPGA using a counter-based, edge-triggered timing rule: symbol transitions are detected by a first-difference (slope) operator, which re-anchors a counter and schedules symbol-center decisions. We also describe a measurement-driven offline calibration of timing-relevant parameters <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mi>θ</mi>\u0000 <mo>=</mo>\u0000 <mo>[</mo>\u0000 <msub>\u0000 <mrow>\u0000 <mi>T</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>Δ</mi>\u0000 </mrow>\u0000 </msub>\u0000 <mo>,</mo>\u0000 <msub>\u0000 <mrow>\u0000 <mi>n</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>c</mi>\u0000 </mrow>\u0000 </msub>\u0000 <mo>,</mo>\u0000 <msub>\u0000 <mrow>\u0000 <mi>L</mi>\u0000 </mrow>\u0000 <mrow>\u0000 <mi>min</mi>\u0000 </mrow>\u0000 </msub>\u0000 <mo>]</mo>\u0000 </mrow>\u0000 <annotation>$$ boldsymbol{theta} =left[{T}_{Delta},{n}_c,{L}_{mathrm{min}}right] $$</annotation>\u0000 </semantics></math>. The formulation is solver-agnostic; in our scripts we employ genetic algorithm (GA) and ant colony optimization (ACO) and use their agreement as a robustness check. From captured training streams we report the optimized slope threshold versus distance and outline a practical deployment path via a compact power-indexed look-up table (LUT) driven by a preamble-based received-power indicator. On a Xilinx Zynq-7000 FPGA, the complete design occupies 9.31% LUTs and 7.17% flip-flops, demonstrating feasibility for low-cost VLC front-ends. Beyond the hardware prototype, we develop a measurement-anchored link-level simulation that reproduces the measured slope-threshold-versus-distance characteristic (<span></span><math>\u0000 <semantics>\u0000 ","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146180","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Hybrid Multi-Gateway Authentication Protocol for 6LoWPAN-Based Marine Wireless Sensor Networks","authors":"Wenfeng Huang,&nbsp;Si Chen","doi":"10.1002/dac.70623","DOIUrl":"https://doi.org/10.1002/dac.70623","url":null,"abstract":"<div>\u0000 \u0000 <p>This paper proposes a secure and efficient three-factor authentication scheme to address the security issues in the integration scenario of multi-gateway wireless sensor networks (WSNs) and 6LoWPAN in marine Internet of Things (IoT). Existing approaches exhibit vulnerabilities to cryptographic breaches, single-point failures, high computational costs, and inefficient long-distance transmission in maritime settings. To mitigate these limitations, we integrate blockchain technology, elliptic curve cryptography (ECC), the Chinese Remainder Theorem (CRT), and a dynamic credential update mechanism to achieve lightweight strong authentication. The scheme supports cross-gateway collaborative authentication to avoid single point of failure and optimizes energy consumption through 6LoWPAN header compression. Security analyses, including BAN logic verification, informal security analyses, and ProVerif validation, demonstrate that the proposed scheme resists cryptographic attacks (e.g., replay and man-in-the-middle attacks) and privilege escalation attacks while achieving anonymity and forward secrecy, thereby ensuring secure mutual authentication and key agreement. Experiments demonstrate 40.5% lower computational costs, 62.2% reduced communication overheads, and 11.7% lower storage overheads compared with the most comparable existing multi-gateway scheme, proving its suitability for resource-constrained marine WSNs. This study provides a practical solution for secure data collection in marine IoT, while also meeting lightweight communication requirements.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146182","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Edge-Based Information-Centric Networking for Enhanced Message Discrimination in Vehicular Ad-Hoc Networks","authors":"Hari Krishna Chilakala,&nbsp;Boddepalli Kiran Kumar","doi":"10.1002/dac.70625","DOIUrl":"https://doi.org/10.1002/dac.70625","url":null,"abstract":"<div>\u0000 \u0000 <p>Vehicular Ad Hoc Networks (VANETs) are central to Intelligent Transportation Systems (ITS), but practical deployment remains constrained by communication latency, scalability, and privacy requirements. This study develops an edge-based Information-Centric Networking (ICN) framework integrated with blockchain technology. Raspberry Pi units equipped with cameras perform real-time incident detection and classification using Convolutional Neural Networks (CNN) and You Only Look Once v8 (YOLOv8). Frame extraction, noise reduction, and data augmentation increased the reported detection accuracy from 70% to 97%. Severity-based incident prioritization reduced latency to 112 ms in low-density networks and 128 ms in high-density networks, while packet loss decreased from 12.12% to 6.34% and throughput increased from 600 to 700 Mbps. The ICN layer also enabled high-priority alerts to reach vehicle dashboards in less than 1 s. The evaluated configuration scaled to 400 mobile routers and 20 access points while maintaining low latency and stable communication. These findings indicate that the proposed architecture can support real-time, secure, and efficient vehicular communication in ITS environments.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146248","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Adaptive Reinforcement Learning-Based Energy Efficient Clustering and Resource Allocation Mechanism in Ultra-Dense Network","authors":"Solayan Kaviarasan,&nbsp;Sandhiya Balamurugan,&nbsp;N. Mageshkumar,&nbsp;Megalan Leo Leon,&nbsp;Vivek Chidambaram","doi":"10.1002/dac.70622","DOIUrl":"https://doi.org/10.1002/dac.70622","url":null,"abstract":"<div>\u0000 \u0000 <p>Due to the quick enhancement of the 5th Generation (5G) wireless communications, the user count is enhancing relatively. So, Ultra-Dense Networks (UDNs) are becoming very significant for assisting various users and enhancing mission-critical applications. To link numerous user systems and offer better data rates, the UDN is referred to as an effective innovation in 5G. It boosts the overall network functionality by enhancing the throughput of the system and managing the load balance of the system. But, the enhanced power utilization and the interference of the UDN because of the deeply installed Base Stations (BSs) are unavoidable. In order to tackle the interference and computation issues in the UDN, a clustering procedure is suggested. In the resource allocation process, the clustering procedure helps to tackle the computational issues by converting the entire cluster into sub-clusters. But, these techniques face more issues in terms of users' Quality of Service (QoS), and they also lag in ensuring the system's transfer efficiency. Thus, to tackle these difficulties, new energy-efficient clustering and resource allocation mechanisms for UDN have been introduced in this paper utilizing adaptive deep learning. First, an optimal clustering process is performed to choose the clusters optimally using Modified Hybrid Leader-based Optimization (MHLO). Moreover, several multi-objective functions are derived using MHLO and this process also supports managing the traffic load among the clusters. Subsequently, in order to enhance convergence and minimize computational complexity, resource allocation is performed in UDN. For this objective, Deep Adaptive Reinforcement Learning (DARL) is employed, where the network parameters are optimized by the MHLO algorithm. In the end, numerical and experimental research is carried out on the developed energy-efficient clustering and routing model over diverse traditional algorithms and techniques. The developed framework MHLO-DARL accomplished higher throughput by 3.4%, a success rate of 97%, and energy efficiency of 0.85%, which seems to be better than recent techniques like GAN-DDQN, DDQN, STPD-RL, and MDQN-MAR. Hence, the validation outcomes showed that the suggested mechanism is more efficient in allocating the resources and executing clustering procedures in the complex environment without affecting communication in a network.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146247","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Compact ACS-Fed IDC-Loaded ELC Metamaterial Inspired Quad-Port MIMO Antenna for Sub-6GHz 5G Applications","authors":"Kanakavalli Harshasri,&nbsp;Ramasamy Pandeeswari","doi":"10.1002/dac.70618","DOIUrl":"https://doi.org/10.1002/dac.70618","url":null,"abstract":"<div>\u0000 \u0000 <p>A novel compact quad-port asymmetric coplanar strip (ACS) fed interdigital capacitor (IDC) loaded electric-inductive capacitor (ELC) metamaterial multiple-input–multiple-output (MIMO) is designed. The electrically small IDC loaded ELC metamaterial inspired quad band single antenna (0.16 λ₀ × 0.1 λ₀) is explored to implement the compact MIMO configuration. The proposed MIMO antenna comprises of four port ACS-fed IDC loaded ELC metamaterial placed orthogonal to each other with footprint of (0.29 λ₀ × 0.29 λ₀). A defected ground structure (DGS) enhanced the decoupling between multiple antennas, providing greater than 30 dB isolation across the operating bands with a spacing of 0.03 λ₀ between antennas. The equivalent circuit for the proposed MIMO antenna is developed to validate the simulated results. The good agreement between the simulated results using ANSYS Electronics simulation and the measured results on the fabricated prototype is validated. The proposed MIMO antenna operates for quad band frequencies 1.2–1.8, 2.1–2.8, 3.2–3.8, and 5.1–5.9 GHz for the application of sub-6GHz 5G New Radio (NG) n51/n53/n78/n46 bands. The computed diversity metrics, such as the envelope correlation coefficient (ECC) &lt; 0.01, diversity gain (DG) &gt; 9.99 dB, total active reflection coefficient (TARC) &lt; −10 dB, channel capacity loss (CCL) &lt; 0.40 b/s/Hz, and the mean effective gain (MEG) &lt; −3 dB, ensure good diversity performance.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145985","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Scheduling Oriented Resource Allocation Using Backscattered NOMA for Heterogeneous Network","authors":"Shilpi,&nbsp;Sachin Kumar,&nbsp;Sudhanshu Tyagi,&nbsp;Sudeep Tanwar","doi":"10.1002/dac.70612","DOIUrl":"https://doi.org/10.1002/dac.70612","url":null,"abstract":"<div>\u0000 \u0000 <p>Growing areas in the wireless communication systems are mainly rise in connectivity, automation, connected devices, artificial intelligence, etc., have attracted the interest of researchers. Nowadays, non-orthogonal multiple access (NOMA) is thoroughly employed to improve network capabilities. A combination of NOMA with backscatter communication (BackCom) provides new prospects for large number of connected device under 5G and beyond. In a single cell wireless network, multiple users communicate with a single base station. Because resources like bandwidth, transmit power, and time slots are limited, the network must allocate these resources efficiently to maximize performance while ensuring fairness among users. Fairness and inter-user interference, especially in NOMA based systems are main resource allocation challenges. To overcome these problems, we have used resource allocation scheme in the proposed approach. In this paper, we considered a single cell wireless communication model with heterogeneous users. To get the optimum throughput, proportional fair scheduling technique is used. The proposed technique is used to allocate the resources by using fair metric for each user. Simulation results shows that the proposed work achieved 13.85% improvement in throughput as compared to orthogonal multiple access technique.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Wavelet-Aided OTFS With Improper Gaussian Noise","authors":"Ayse Elif Canbilen","doi":"10.1002/dac.70616","DOIUrl":"https://doi.org/10.1002/dac.70616","url":null,"abstract":"<div>\u0000 \u0000 <p>Sixth-generation (6G) wireless communication is expected to include much higher mobility usage scenarios compared with previous generations. This situation brings with it challenges such as Doppler and hardware-induced distortion effects, which traditional methods are insufficient to handle. In this study, wavelet-aided orthogonal time-frequency space (W-OTFS) modulation, known for its resistance to Doppler shifts, is addressed under the effect of improper Gaussian noise (IGN) originating from hardware faults, which is largely neglected in the literature. Considering a highly mobile 6G scenario, a hard-decision-based widely linear minimum mean square error (WL-MMSE) detector is designed to evaluate the bit error rate (BER) of the proposed W-OTFS system, and the simulation results are presented. In addition to Daubechies and Haar wavelets, which are frequently preferred in W-OTFS applications, results obtained with different orthogonal wavelet types are also introduced. The extensive simulation results demonstrate that the W-OTFS provides more than 5 dB gain for achieving a BER value of <span></span><math>\u0000 <semantics>\u0000 <mrow>\u0000 <mn>1</mn>\u0000 <msup>\u0000 <mrow>\u0000 <mn>0</mn>\u0000 </mrow>\u0000 <mrow>\u0000 <mo>−</mo>\u0000 <mn>2</mn>\u0000 </mrow>\u0000 </msup>\u0000 </mrow>\u0000 <annotation>$$ 1{0}^{-2} $$</annotation>\u0000 </semantics></math> compared with the traditional OTFS, regardless of the wavelet type. Furthermore, W-OTFS is proven to resolve the high PAPR issue in OTFS. Depending on the selected wavelet type, a minimum PAPR reduction of 2.5 dB was achieved compared with OTFS.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-10-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149145804","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An Energy-Efficient Multiparameter Clustering and Routing Framework for WSNs Using Adaptive Starfish Optimization Algorithm and Spider-Tailed Horned Viper Optimization","authors":"Renaldo Maximus A,&nbsp;Balaji S","doi":"10.1002/dac.70613","DOIUrl":"https://doi.org/10.1002/dac.70613","url":null,"abstract":"<div>\u0000 \u0000 <p>Wireless sensor networks (WSNs) have become an essential component of environmental monitoring, military surveillance, industrial automation, and smart city applications. However, the limited energy capacity of sensor nodes and inefficient clustering and routing mechanisms significantly affect network lifetime, communication reliability, and quality of service (QoS). Existing approaches often rely on a limited number of parameters for cluster-head selection and routing decisions, resulting in unbalanced energy consumption, frequent cluster-head failures, increased communication overhead, and reduced network performance. To overcome these limitations, this work proposes an energy-efficient multiparameter clustering and routing framework that integrates the enhanced grid-based clustering algorithm (EGBCA), improved starfish optimization algorithm (ISFOA), and adaptive spider-tailed horned viper optimization (ASTHVO). EGBCA forms balanced clusters, while ISFOA selects optimal cluster heads using multiple parameters, including node energy, residual energy, distance to the base station, node degree, and intra-cluster distance. Subsequently, ASTHVO identifies reliable and energy-efficient routing paths to improve data transmission efficiency and network stability. Simulation results obtained in MATLAB demonstrate that the proposed framework achieves a network lifetime of 5500 rounds, energy consumption of 38 mJ, end-to-end delay (E2ED) of 3.5 ms, packet delivery ratio (PDR) of 98%, throughput of 0.9 Mbps, and bit error rate of 3%, outperforming existing methods across key QoS metrics. The proposed framework effectively improves energy efficiency, communication reliability, and network longevity, making it a promising solution for next-generation WSN deployments.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-09-30","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Privacy-Preserving Federated Deep Learning for 6G Network Security Monitoring","authors":"J. K. Kanimozhi,&nbsp;M. I. Shiny,&nbsp;A. Senthilkumar,&nbsp;Suneet Joshi","doi":"10.1002/dac.70609","DOIUrl":"https://doi.org/10.1002/dac.70609","url":null,"abstract":"<div>\u0000 \u0000 <p>Deep federated learning (DFL) has emerged as an effective paradigm for privacy-preserving decentralized intelligence in sixth-generation mobile networks. Increasing deployment of intelligent network services introduces challenges associated with high communication overhead, susceptibility to model poisoning attacks, limited interpretability, and inefficient hyperparameter optimization, which reduce the reliability of federated intrusion detection. To address these limitations, an integrated framework combining Explainable Fast Topic-aware Temporal Dual-path Convolutional Attention (EFTTDCA) and the Artificial Circulation System Algorithm (ACSA) is presented. The dual-path attention architecture captures both short-term malicious traffic patterns and long-term temporal dependencies to improve intrusion detection in virtual network functions, whereas ACSA performs adaptive hyperparameter optimization for stable convergence and reduced computational complexity. A lightweight federated communication mechanism with secure model-update transmission and an explainability module further enhances privacy, transparency, and deployment efficiency. Experimental evaluation using the InSDN, CICIDS2017, Kitsune, 6G mIoT Network Traffic, and 6G-AI-EdSecure datasets achieves an average detection accuracy of 98.98%, precision of 98.92%, recall of 98.94%, and F1-score of 98.95%, together with lower communication overhead, faster convergence, and improved resource efficiency compared with existing federated intrusion detection approaches. These findings demonstrate that the proposed framework provides accurate, secure, interpretable, and computationally efficient intrusion detection for privacy-preserving 6G virtual network environments.</p>\u0000 </div>","PeriodicalId":13946,"journal":{"name":"International Journal of Communication Systems","volume":"39 16","pages":""},"PeriodicalIF":1.8,"publicationDate":"2026-09-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"149146990","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}