IEEE Networking Letters最新文献_第7页

Enabling Seamless Integration of ML-Based Network Functions Into the Network Dataplane 实现基于机器学习的网络功能与网络数据面的无缝集成

IEEE Networking Letters Pub Date : 2025-12-31 DOI: 10.1109/LNET.2025.3649955

Sourabh Singh;Kunvar Kanhaiya;Pralhad Magadum;Rituraj Patel;Aniruddha Singh Kushwaha

引用次数: 0

UE Localization and UAV-BS Placement via GPR-Aided RSSI-TOA Fusion With a Lightweight Q-Learning Controller 基于gpr辅助RSSI-TOA融合的无人机- bs定位与轻量化Q-Learning控制器

IEEE Networking Letters Pub Date : 2025-12-31 DOI: 10.1109/LNET.2025.3649892

Pushpak Shukla;Jitendra Kumar;Shailendra Shukla

{"title":"UE Localization and UAV-BS Placement via GPR-Aided RSSI-TOA Fusion With a Lightweight Q-Learning Controller","authors":"Pushpak Shukla;Jitendra Kumar;Shailendra Shukla","doi":"10.1109/LNET.2025.3649892","DOIUrl":"https://doi.org/10.1109/LNET.2025.3649892","url":null,"abstract":"In this letter, we propose a lightweight framework for rapid Uncrewed Aerial Vehicle Base-Station (UAV-BS) deployment that couples noise-resilient User Equipment (UE) localization with adaptive power-position control. Localization fuses Received Signal Strength Indicator (RSSI) and Time of Arrival (TOA) using Gaussian process regression (GPR) aided, inverse-variance weighting, GPR corrects RSSI residual bias and supplies uncertainty, while TOA provides geometric anchoring, yielding robustness to multipath and Non-Line-of-Sight (NLOS) with modest added complexity. The deployment module employs a compute-efficient, discrete-action controller based on Paired Whale Optimization Q-Learning Agent (PWOQLA) initialization with logistic exploration, enabling edge-friendly, CPU-only operation. On a 1 km2 scenario with 1000 devices, the fusion pipeline attains sub-meter accuracy (<inline-formula> <tex-math>$approx 0.33$ </tex-math></inline-formula> m mean error), reducing error by ~94.5% versus weighted/iterative trilateration (~6 m). Under LOS/NLOS, energy, and QoS constraints, the controller converges faster and achieves tighter placement than DRL baselines, showing its suitability for time-critical, resource-limited disaster recovery.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"59-63"},"PeriodicalIF":0.0,"publicationDate":"2025-12-31","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147280900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Semantic-Aware Cooperative Communication and Computation Framework in Vehicular Networks 车辆网络中语义感知的协同通信与计算框架

IEEE Networking Letters Pub Date : 2025-12-25 DOI: 10.1109/LNET.2025.3648419

Jingbo Zhang;Maoxin Ji;Qiong Wu;Pingyi Fan;Kezhi Wang;Wen Chen

引用次数: 0

ULNet: Federated Unlearning for SDN Control-Plane Anomaly Detection 用于SDN控制平面异常检测的联合学习

IEEE Networking Letters Pub Date : 2025-12-17 DOI: 10.1109/LNET.2025.3645209

Hai Anh Tran

{"title":"ULNet: Federated Unlearning for SDN Control-Plane Anomaly Detection","authors":"Hai Anh Tran","doi":"10.1109/LNET.2025.3645209","DOIUrl":"https://doi.org/10.1109/LNET.2025.3645209","url":null,"abstract":"The increasing programmability of modern networks through Software-Defined Networking (SDN) introduces new vulnerabilities at the control plane, necessitating efficient and secure anomaly detection solutions. In this letter, we propose ULNet, a novel framework that combines coreset-assisted lightweight training with federated unlearning to detect and adapt to anomalies in distributed SDN control planes. Our approach enables SDN controllers to collaboratively train lightweight anomaly detection models using compact coreset representations, significantly reducing communication and computational overhead. To address controller compromise or poisoning, ULNet integrates a Forget-on-Compression mechanism, allowing selective removal of malicious or outdated knowledge without full model retraining. The proposed framework ensures adaptive, privacy-preserving, and scalable detection while remaining compliant with the operational constraints of modern network infrastructures. Experimental results on realistic SDN control-plane datasets demonstrate that ULNet achieves competitive detection performance with up to 70% reduction in communication cost and effective unlearning of malicious contributions.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"8 ","pages":"5-9"},"PeriodicalIF":0.0,"publicationDate":"2025-12-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147280894","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Toward Secure 5G/6G Networks: Comparing Multimodal Fusion Methods for Attack Detection 迈向安全的5G/6G网络：比较攻击检测的多模态融合方法

IF 3.3

IEEE Networking Letters Pub Date : 2025-12-01 Epub Date: 2025-10-01 DOI: 10.1109/LNET.2025.3616521

Loukas Ilias;George Doukas;Christos Ntanos;Dimitris Askounis

{"title":"Toward Secure 5G/6G Networks: Comparing Multimodal Fusion Methods for Attack Detection","authors":"Loukas Ilias;George Doukas;Christos Ntanos;Dimitris Askounis","doi":"10.1109/LNET.2025.3616521","DOIUrl":"https://doi.org/10.1109/LNET.2025.3616521","url":null,"abstract":"The rapid development of 5G and emerging 6G networks introduces advanced security threats (e.g., DDoS, eavesdropping, jamming, etc.), necessitating advanced intrusion detection systems. Current studies use outdated benchmark datasets that do not capture the dynamic, AI-driven traffic of these networks. Additionally, they often rely on payload data for intrusion detection; however, in 5G/6G networks, payloads are typically encrypted, limiting the applicability and effectiveness of these approaches. While some research explores fusion methods, they typically overlook crucial inter- and intra-modal interactions. To address these limitations, this letter applies multimodal fusion methods on a publicly available dataset reflecting realistic 5G/6G conditions. Features are grouped into packet-related, time-related, and length-related modalities. Fusion methods, including bilinear pooling, gated multimodal unit, and block-term tensor decomposition, are employed. Results show that block term tensor decomposition achieves a weighted F1-score of 99.08%, outperforming the other fusion methods by 8.08-16.74%. This letter also provides a comparative discussion on the computational complexity of each fusion method. Finally, a series of ablation experiments is conducted to prove the effectiveness of the introduced approach.","PeriodicalId":100628,"journal":{"name":"IEEE Networking Letters","volume":"7 4","pages":"337-341"},"PeriodicalIF":3.3,"publicationDate":"2025-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=11186159","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"148510671","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Guest Editorial Special Issue on Security and Privacy Issues in Networking in the Age of Artificial Intelligence 《人工智能时代网络中的安全与隐私问题》特刊

IF 3.3

IEEE Networking Letters Pub Date : 2025-12-01 Epub Date: 2026-01-16 DOI: 10.1109/LNET.2025.3640787

Keshav Sood;Youyang Qu;Shui Yu;Song Guo;Yao Liu;Pierangela Samarati

引用次数: 0

Federated Learning Assisted Edge Caching Scheme Based on Lightweight Architecture DDPM 基于轻量级体系结构DDPM的联邦学习辅助边缘缓存方案

IF 3.3

IEEE Networking Letters Pub Date : 2025-12-01 Epub Date: 2025-08-18 DOI: 10.1109/LNET.2025.3599196

Xun Li;Qiong Wu;Pingyi Fan;Kezhi Wang;Nan Cheng;Khaled B. Letaief

引用次数: 0

Context-Aware Rate Adaptation for Predictable Flying Networks Using Contextual Bandits 使用上下文强盗的可预测飞行网络的上下文感知速率自适应

IF 3.3

IEEE Networking Letters Pub Date : 2025-12-01 Epub Date: 2025-08-28 DOI: 10.1109/LNET.2025.3603744

Ruben Queiros;Megumi Kaneko;Helder Fontes;Rui Campos

引用次数: 0

Exemplifying Emerging Phishing: QR-Based Browser-in-the-Browser (BiTB) Attack 举例说明新兴的网络钓鱼：基于qr的浏览器中浏览器（BiTB）攻击

IF 3.3

IEEE Networking Letters Pub Date : 2025-12-01 Epub Date: 2025-09-03 DOI: 10.1109/LNET.2025.3605640

Muhammad Wahid Akram;Keshav Sood;Muneeb Ul Hassan;Basant Subba

引用次数: 0

Robustness Analysis of Watermarking Techniques for LLM-Generated Code llm生成代码中水印技术的鲁棒性分析

IF 3.3

IEEE Networking Letters Pub Date : 2025-12-01 Epub Date: 2025-10-01 DOI: 10.1109/LNET.2025.3616325

Di Cao;Shigang Liu;Jun Zhang;Yang Xiang

引用次数: 0