Journal of Network and Computer Applications最新文献

Proactive Service Migration in Vehicular Edge Computing via Map-Aware Mobility Prediction and Dynamic Action-Space Deep Reinforcement Learning 基于地图感知移动预测和动态动作空间深度强化学习的车辆边缘计算主动服务迁移

IF 8.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-10-01 DOI: 10.1016/j.jnca.2026.104601

Shaojie Han,Shengchao Su,Baoxuan Du

引用次数: 0

Noise-utility-detectability trade-off: A trilemma in differentially private federated learning for IoT networks 噪声-效用-可检测性权衡：物联网网络差异私有联邦学习的三难困境

IF 8.7 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-10-01 DOI: 10.1016/j.jnca.2026.104596

Smriti Priyadarshani,Prasanta K. Jana

引用次数: 0

ChatPRE: Knowledge-aware protocol analysis with LLMs for intelligent segmentation ChatPRE：知识感知协议分析与llm智能分割

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-05-01 Epub Date: 2026-02-13 DOI: 10.1016/j.jnca.2026.104426

Guoyu Huo , Yuyao Huang, Fei Kang, Hui Shu

{"title":"ChatPRE: Knowledge-aware protocol analysis with LLMs for intelligent segmentation","authors":"Guoyu Huo , Yuyao Huang, Fei Kang, Hui Shu","doi":"10.1016/j.jnca.2026.104426","DOIUrl":"10.1016/j.jnca.2026.104426","url":null,"abstract":"<div><div>In the field of network security, protocol reverse engineering (PRE) is one of the core technologies. However, existing PRE methods face two key challenges: (1) heuristic-based field segmentation lacks robustness and requires extensive manual tuning for complex protocols, and (2) insufficient semantic rules hinder accurate inference of protocol semantics. To address these issues, this paper introduces ChatPRE, a novel three-stage framework that integrates program analysis with large language models (LLMs). In the field segmentation stage, dynamic taint tracking is combined with variable mapping on IDA pseudo-C code. Specifically, variable consistency is used instead of heuristic rules to locate field boundaries, while variable repetition clustering is applied to identify high-level semantic fields. For semantic inference, an agent workflow feeds pseudo-C code logic, field content, and contextual features into LLMs to infer functional semantics. Finally, field boundaries and annotations are globally refined through a re-inference step. Experiments on six standard protocols and one malware protocol demonstrate significant improvements over four baseline tools: ChatPRE achieves 11%–46% higher field segmentation accuracy and reduces segmentation errors by 63%–70%. Semantic inference accuracy is improved by 14%–45%. This work provides an innovative approach to PRE, which leverages LLMs to enhance both structural parsing and semantic understanding.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"249 ","pages":"Article 104426"},"PeriodicalIF":8.0,"publicationDate":"2026-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146192470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Immersive intelligence: ST-GNN guided and RL-optimized multimodal intent-driven Kubernetes Orchestration for 6G resource management 沉浸式智能：用于6G资源管理的ST-GNN引导和rl优化的多模态意图驱动的Kubernetes编排

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-02-05 DOI: 10.1016/j.jnca.2026.104440

Muhammad Asif , Wang-Cheol Song , Yeo-Chan Yoon

{"title":"Immersive intelligence: ST-GNN guided and RL-optimized multimodal intent-driven Kubernetes Orchestration for 6G resource management","authors":"Muhammad Asif , Wang-Cheol Song , Yeo-Chan Yoon","doi":"10.1016/j.jnca.2026.104440","DOIUrl":"10.1016/j.jnca.2026.104440","url":null,"abstract":"<div><div>The rapid evolution of 6G-enabled Metaverse applications such as holographic conferencing, digital twins, and immersive collaboration demands ultra-low latency, high reliability, and intelligent orchestration across distributed cloud infrastructures. Existing Kubernetes autoscalers rely on reactive threshold rules that cannot interpret user behavior or adapt to the dynamic resource patterns of multimodal workloads in real time. This article presents a unified intent-assured orchestration framework that combines spatio-temporal forecasting, multimodal understanding, and Reinforcement learning (RL) within a Kubernetes-native control loop. A Spatio Temporal Graph Neural Network (ST-GNN) forecasts resource demands across the core, regional, and edge zones, guiding multimodal models, BLIP, Wav2Vec2, and KAN, to generate context-sensitive intents from visual, auditory, and motion data. These intents are validated by a Semantic Structural Intent Verifier (SSIV) that ensures semantic and structural consistency before policy translation through the Intent-Based Networking (IBN) layer. The RL controller then optimizes these verified policies for scaling, placement, and allocation across distributed clusters. Experiments on heterogeneous multimodal workloads show 19% fewer SLA violations, 15% lower CPU provisioning, and 21% latency reduction compared to baseline autoscalers. Aligned with TM Forum and ETSI ZSM principles for closed-loop automation, the proposed design provides a scalable and transparent pathway toward fully autonomous, 6G O-Cloud infrastructures.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104440"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134548","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Pulse: Multi-objective scheduling of service-based applications in multi-cluster cloud–edge–IoT infrastructures 脉冲：多集群云边缘物联网基础设施中基于服务的应用的多目标调度

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-02-10 DOI: 10.1016/j.jnca.2026.104439

Marlon Etheredge, Juan Aznar Poveda, Stefan Pedratscher, Abolfazl Younesi, Thomas Fahringer

{"title":"Pulse: Multi-objective scheduling of service-based applications in multi-cluster cloud–edge–IoT infrastructures","authors":"Marlon Etheredge, Juan Aznar Poveda, Stefan Pedratscher, Abolfazl Younesi, Thomas Fahringer","doi":"10.1016/j.jnca.2026.104439","DOIUrl":"10.1016/j.jnca.2026.104439","url":null,"abstract":"<div><div>The rapid growth of cloud computing and the expansion of edge and IoT technologies are becoming essential for meeting the performance, scalability, and latency requirements of modern distributed service-based applications. While these applications facilitate the accommodation of real-world workloads, their placement across a computing continuum spanning the cloud, edge, and IoT remains challenging. Existing service scheduling works often rely on simulations or orchestration systems limited to a single cluster. While simulations fail to capture real-world constraints, single-cluster orchestration systems introduce significant overhead and cannot capture the heterogeneity, network latency, and cross-cluster dependencies across cloud, edge, and IoT layers. In this paper, we introduce Pulse, a fully distributed scheduling system designed to optimize the deployment of distributed service-based applications across multi-cluster environments. Pulse leverages a two-phase distributed multi-objective optimization approach: locally optimizing for monetary cost and fairness within clusters, and globally optimizing for monetary cost and latency across multiple clusters. Pulse is built atop a lightweight orchestration framework, which enables service coordination across cloud, edge, and IoT layers, ensuring adaptability to heterogeneous infrastructures and the latency among geo-distributed clusters. To validate our approach, we conduct a comprehensive real-world evaluation on the Grid’5000 infrastructure, demonstrating that Pulse outperforms state-of-the-art scheduling methods by improving total resource utilization by 34.5%, reducing monetary cost by 82.6%, and lowering the average end-to-end network latency among services by 75.0%. These results highlight Pulse’s effectiveness in managing large-scale, service-based applications in realistic, multi-cluster environments.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104439"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146152962","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Dynamic dependency-aware vulnerability and patch management for critical interconnected systems 关键互联系统的动态依赖感知漏洞和补丁管理

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-01-27 DOI: 10.1016/j.jnca.2026.104436

Umar Sa’ad , Woongsoo Na , Nhu-Ngoc Dao , Sungrae Cho

{"title":"Dynamic dependency-aware vulnerability and patch management for critical interconnected systems","authors":"Umar Sa’ad , Woongsoo Na , Nhu-Ngoc Dao , Sungrae Cho","doi":"10.1016/j.jnca.2026.104436","DOIUrl":"10.1016/j.jnca.2026.104436","url":null,"abstract":"<div><div>Critical infrastructure systems characterized by complex interdependencies face significant challenges in vulnerability management due to cascading risk propagation through interconnected components. Traditional approaches that individually prioritize vulnerabilities inefficiently manage these dependency structures, leading to suboptimal security outcomes. This paper introduces an adaptive dependency-aware patching technique (ADAPT), a dynamic vulnerability and patch management framework that integrates formal dependency modeling with reinforcement learning to optimize patching strategies for critical interconnected systems. The proposed approach employs a mathematical formulation to capture direct and transitive dependencies via reachability matrices, enabling precise quantification of cascading risk propagation. The framework dynamically adapts patching decisions under resource constraints using proximal policy optimization within a constrained Markov decision process formulation. Comprehensive evaluation across 954 system configurations and six baseline strategies demonstrates consistent performance improvements, with 5.5% advantage over state-of-the-art NSGA-II multi-objective optimization while achieving 1513× computational speedup. Optimality gap analysis reveals 4.33% average deviation from theoretical bounds, validating the framework’s near-optimal solution quality. A critical infrastructure case study confirms practical applicability, with ADAPT achieving 89.7% risk reduction compared to 86.4% for sophisticated baseline methods, while enabling real-time decision-making through sub-second computation times. The results demonstrate superior performance under high dependency density and resource constraints, highlighting the framework’s suitability for environments where cascading failures pose operational threats.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104436"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146056010","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

ILAD: A hardware-efficient authenticated encryption scheme for VANET applications based on Ascon ILAD：基于Ascon的VANET应用程序的硬件高效身份验证加密方案

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-01-22 DOI: 10.1016/j.jnca.2026.104428

Jiali Tang, Lang Li, Xingqi Yue

{"title":"ILAD: A hardware-efficient authenticated encryption scheme for VANET applications based on Ascon","authors":"Jiali Tang, Lang Li, Xingqi Yue","doi":"10.1016/j.jnca.2026.104428","DOIUrl":"10.1016/j.jnca.2026.104428","url":null,"abstract":"<div><div>The rapid expansion of Vehicular Ad Hoc Networks (VANETs) has intensified the need for secure and efficient communication protocols, particularly in resource-constrained environments. Conventional encryption schemes offer strong security but frequently underperform in terms of computational efficiency and resource utilization due to their high complexity and resource demands. Ascon, a widely adopted lightweight encryption algorithm, provides robust security but poses challenges in hardware optimization. This paper introduces ILAD, a hardware-efficient authenticated encryption algorithm specifically designed for VANET applications. ILAD improves security and reduces resource overhead by optimizing key components within the round function and restructuring the sponge construction to enhance module reusability and hardware efficiency. The S-box is constructed using a Tent map-based chaotic system and refined through iterative optimization to ensure strong cryptographic properties and minimal resource usage, implemented with area-saving MOAI1 logic gates. Experimental results demonstrate that ILAD achieves a 36.1% reduction in S-box area and a 15.2% reduction in total area under UMC <span><math><mrow><mn>0</mn><mo>.</mo><mn>18</mn><mspace></mspace><mi>μ</mi><mi>m</mi></mrow></math></span> process technology. The algorithm has been successfully deployed on the i.MX6ULL_PRO development board, a Cortex-A7-based low-power processor platform, where it achieved stable performance with low latency and energy consumption. Comprehensive security evaluations confirm ILAD’s robustness against various cryptanalytic attacks, making it a strong candidate for secure and lightweight VANET deployments.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104428"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146033298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Generalized detection of DDoS attack patterns using machine learning models 使用机器学习模型的DDoS攻击模式的广义检测

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-02-06 DOI: 10.1016/j.jnca.2026.104441

Razvan Bocu , Maksim Iavich

{"title":"Generalized detection of DDoS attack patterns using machine learning models","authors":"Razvan Bocu , Maksim Iavich","doi":"10.1016/j.jnca.2026.104441","DOIUrl":"10.1016/j.jnca.2026.104441","url":null,"abstract":"<div><div>Distributed Denial of Service (DDoS) attacks, including stealthy Low-Rate DDoS (LRDDoS) variants, pose critical challenges to network security by evading conventional detection systems that rely on traffic volume thresholds. Existing machine learning-based detectors often fail to generalize across diverse attack patterns, suffer from concept drift in evolving traffic, and cannot leverage distributed data due to privacy constraints. To address these limitations, we propose FLD-DDoS, an integrated detection framework based on asynchronous Federated Learning (FL) with Bidirectional LSTM (Bi-LSTM) and adaptive concept drift handling. Our approach enables collaborative model training across multiple network nodes without centralizing sensitive data, while maintaining detection accuracy under changing traffic conditions. The key contributions include: (1) a novel asynchronous FL architecture with intelligent main node selection; (2) a Bi-LSTM classifier enhanced with model drift detection using Kolmogorov–Smirnov testing; (3) a comprehensive evaluation on 800 million real-world corporate network packets showing 99.82% detection accuracy with sub-second latency; (4) experimental comparison demonstrating superiority over six baseline and state-of-the-art methods; (5) a comparative experimental evaluation considering two additional baseline models. The implemented system significantly reduces network load and demonstrates scalable performance with <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mi>n</mi><mo>)</mo></mrow></mrow></math></span> time complexity for the core algorithms, while providing robust protection against both volumetric and stealthy DDoS attacks.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104441"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146134530","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Redefining resilience: A hybrid quantum-fuzzy Deep Q-Network paradigm for perpetual wireless rechargeable sensor networks 重新定义弹性：用于永久无线可充电传感器网络的混合量子模糊深度q -网络范式

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-01-20 DOI: 10.1016/j.jnca.2026.104427

Riya Goyal, Abhinav Tomar

{"title":"Redefining resilience: A hybrid quantum-fuzzy Deep Q-Network paradigm for perpetual wireless rechargeable sensor networks","authors":"Riya Goyal, Abhinav Tomar","doi":"10.1016/j.jnca.2026.104427","DOIUrl":"10.1016/j.jnca.2026.104427","url":null,"abstract":"<div><div>Wireless Rechargeable Sensor Networks (WRSNs) offer a transformative solution to energy constraints in remote and mission-critical Internet of Things (IoT) environments by leveraging Wireless Energy Transfer (WET). However, current state-of-the-art approaches often suffer from limited scalability, inefficient energy scheduling, and inadequate adaptability to dynamic network states. Key challenges such as optimal mobile charger (MC) deployment, cooperative multi-agent scheduling, and intelligent threshold determination for on-demand charging remain insufficiently addressed—particularly in large-scale, real-time WRSNs. This paper proposes a novel hybrid framework that integrates Deep Q-Networks (DQNs) with a Quantum-Inspired Fuzzy Logic (QIFL) model for resilient and perpetual energy replenishment. To overcome spatial and load imbalances, an Enhanced Black Hole Optimization (EBHO) technique is used for partitioning the network and deploying MCs optimally. Unlike prior work, the proposed approach dynamically adapts charging thresholds using QIFL, capturing nonlinear energy consumption patterns and spatial heterogeneity. A multi-agent DQN model is deployed to handle high-dimensional state–action spaces, facilitating decentralized decision-making under uncertainty. Further, a proximity-aware charging mechanism, empowered by an improved Adaptive Genetic Algorithm (AGA), ensures real-time task redistribution among MCs, maintaining network longevity and zero sensor node failure. Experimental results demonstrate a 19.59% improvement in energy utilization and complete elimination of dead nodes compared to leading benchmarks, establishing the superiority of the proposed scheme for large-scale, adaptive, and sustainable WRSN operations.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104427"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001755","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust and energy-aware detection of Mirai botnet for future 6G-enabled IoT networks 为未来支持6g的物联网网络提供强大的Mirai僵尸网络和能量感知检测

IF 8 2区计算机科学

Journal of Network and Computer Applications Pub Date : 2026-04-01 Epub Date: 2026-02-09 DOI: 10.1016/j.jnca.2026.104438

Zainab Alwaisi , Tanesh Kumar , Simone Soderi

{"title":"Robust and energy-aware detection of Mirai botnet for future 6G-enabled IoT networks","authors":"Zainab Alwaisi , Tanesh Kumar , Simone Soderi","doi":"10.1016/j.jnca.2026.104438","DOIUrl":"10.1016/j.jnca.2026.104438","url":null,"abstract":"<div><div>Next-generation IoT wireless communication systems emphasise the importance and urgent need for energy-efficient security measures, thus requiring a balanced approach to address growing security vulnerabilities and fulfil energy demands in advanced wireless communication networks. However, the evolution of 6G networks and their integration with advanced technologies will revolutionise the IoT ecosystem while simultaneously introducing new security threats such as the Mirai malware, which targets IoT devices, infects multiple nodes, and depletes computational and energy resources. This study introduces a novel security algorithm designed to minimise energy consumption while effectively detecting botnet attacks at the smart device level. This research examines four distinct types of Mirai botnet attacks: scan, UDP, TCP, and ACK flooding.The experimental evaluation was conducted using real IoT device data collected from a Raspberry Pi setup combined with network traffic traces simulating the four Mirai attack scenarios to ensure realistic and reproducible results. Two ML algorithms, SVM and KNN, are employed to detect these botnet attacks, with each algorithm’s detection accuracy and energy efficiency thoroughly assessed. Results indicate that the proposed approach significantly enhances smart device security while minimising energy use. Findings show that the KNN algorithm outperforms SVM in terms of accuracy and energy efficiency for detecting Mirai botnet attacks, achieving detection rates above 99% across various attack types. This study highlights the importance of selecting suitable security techniques for IoT networks to address the evolving threats and energy demands of 6G-enabled wireless communication systems, providing valuable insights for future research.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"248 ","pages":"Article 104438"},"PeriodicalIF":8.0,"publicationDate":"2026-04-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146146704","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0