Aoshuang Ye , Shilin Zhang , Benxiao Tang , Jianpeng Ke , Yiru Zhao , Tao Peng
{"title":"DeFinder: Error-sensitive testing of deep neural networks via vulnerability interpretation","authors":"Aoshuang Ye , Shilin Zhang , Benxiao Tang , Jianpeng Ke , Yiru Zhao , Tao Peng","doi":"10.1016/j.jnca.2025.104212","DOIUrl":"10.1016/j.jnca.2025.104212","url":null,"abstract":"<div><div>DNN testing evaluates the vulnerability of neural networks through <em>adversarial test cases</em>. The developers implement minor perturbations to the seed inputs to generate test cases, which are guided by meticulously designed testing criteria. Nevertheless, current coverage-guided testing methods rely on covering model states rather than analyzing the influence of seed inputs on inducing erroneous behaviors. In this paper, we propose a novel DNN testing method called DeFinder, which generates error-sensitive tests by implementing an explainable framework for neural networks to establish correlations between model vulnerability and seed inputs. By systematically analyzing vulnerable regions within seed inputs, DeFinder significantly improves the test suite’s ability to maximize test coverage and expose errors. To validate the effectiveness of DeFinder, we conduct comprehensive experiments with nine deep neural network models from two popular computer vision datasets. We compare the proposed method with several state-of-the-art DNN testing tools. The experimental results demonstrate that DeFinder improves the error-triggering ratio by up to 58% and increases test coverage by up to 4.3%. For reproducibility, the artifact for this work is available at public repository: <span><span>https://github.com/Konatazz/DeFinder</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104212"},"PeriodicalIF":7.7,"publicationDate":"2025-05-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147749","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}
{"title":"Mixer-transformer: Adaptive anomaly detection with multivariate time series","authors":"Xing Fang , Yuanfang Chen , Zakirul Alam Bhuiyan , Xiajun He , Guangxu Bian , Noel Crespi , Xiaoyuan Jing","doi":"10.1016/j.jnca.2025.104216","DOIUrl":"10.1016/j.jnca.2025.104216","url":null,"abstract":"<div><div>Anomaly detection is crucial for maintaining the stability and security of systems. However, anomaly detection systems often generate numerous false positives or irrelevant alerts, which obscure genuine security threats. To both reduce false positives in time series detection and accurately identify the source of anomalies, leveraging artificial intelligence techniques has emerged as a promising solution. These techniques can analyze strong temporal correlations and dynamic variations across different data frames. Existing detection methods face two primary challenges leading to false positives or negatives: (i) detecting anomalies in multivariate time series requires accounting for both temporal dependencies and complex interactions between variables; and (ii) traditional fixed-threshold approaches often struggle to adapt to dynamic environments. To address these issues, this paper proposes an anomaly detection method based on the Mixer-Transformer architecture. By combining the Mixer model with the Anomaly Transformer, the proposed method effectively captures global dependencies by alternately modeling interactions along both the channel and time dimensions, thereby enhancing its ability to extract complex spatiotemporal features. Additionally, an adaptive threshold update mechanism is employed to dynamically adjust the anomaly detection criteria in response to data fluctuations. The F1 scores on three real-world datasets — SMAP, MSL, and PSM — are 97.49%, 95.18%, and 98.20%, respectively. These results demonstrate that the proposed method outperforms existing technologies in reducing false positives and enhancing the detection accuracy of multivariate time series anomaly detection.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104216"},"PeriodicalIF":7.7,"publicationDate":"2025-05-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144147750","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}
Jamal Alotaibi , Omar Sami Oubbati , Mohammed Atiquzzaman , Fares Alromithy , Mohammad Rashed Altimania
{"title":"Optimizing disaster response with UAV-mounted RIS and HAP-enabled edge computing in 6G networks","authors":"Jamal Alotaibi , Omar Sami Oubbati , Mohammed Atiquzzaman , Fares Alromithy , Mohammad Rashed Altimania","doi":"10.1016/j.jnca.2025.104213","DOIUrl":"10.1016/j.jnca.2025.104213","url":null,"abstract":"<div><div>In the context of disaster response and recovery within 6th Generation (6G) networks, achieving both low-latency and energy-efficient communication under compromised infrastructure remains a critical challenge. This paper introduces a novel framework that integrates a solar-powered High-Altitude Platform (HAP) with multiple Unmanned Aerial Vehicles (UAVs) equipped with Reconfigurable Intelligent Surfaces (RISs), significantly enhancing disaster response capabilities. A hybrid approach combining game theory and multi-agent reinforcement learning (MARL) is employed to optimize UAV energy management, RIS control, and the offloading data rates of ground devices (GDs). Specifically, game theory is used to determine optimal task offloading decisions, balancing energy consumption, latency, and computational efficiency, while MARL dynamically guides UAV trajectories and RIS configurations to maintain robust communication links. A key innovation is the RIS ON/OFF mechanism, which conserves energy by switching OFF RISs when not needed, allowing UAVs to recharge during inactive periods and extending operational lifetimes. The proposed framework also demonstrates superior performance in optimizing offloading data rates and minimizing task offloading costs, ensuring efficient resource utilization. Extensive simulations validate the effectiveness of this approach, showing significant improvements in energy efficiency, data processing performance, and overall network reliability compared to traditional methods. These advancements contribute to more reliable and energy-efficient disaster response operations within 6G networks.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104213"},"PeriodicalIF":7.7,"publicationDate":"2025-05-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144108260","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}
Guangquan Zeng , Wan Hu , Yongchao Zhou , Desheng Zheng , Xiaoyu Li , Chuang Shi
{"title":"RCA-SI: A Rapid Consensus Algorithm for Swarm Intelligence in unstable network environments","authors":"Guangquan Zeng , Wan Hu , Yongchao Zhou , Desheng Zheng , Xiaoyu Li , Chuang Shi","doi":"10.1016/j.jnca.2025.104202","DOIUrl":"10.1016/j.jnca.2025.104202","url":null,"abstract":"<div><div>Swarm intelligence systems are a class of distributed systems in which device nodes utilize distributed algorithms to achieve data consensus and execute complex collective tasks. These systems operate in highly dynamic environments, where unstable network conditions, often induced by environmental complexities, can significantly affect the progress and efficiency of data consensus. To tackle this challenge, we propose RCA-SI (Raft-based Consensus Algorithm for Swarm Intelligence), a novel method specifically designed for the task scenarios of swarm intelligence. RCA-SI is designed with a node management protocol and a cluster operation protocol to address the challenge of rapid data consensus in unstable network environments. The correctness of RCA-SI was formally verified using TLA+. Furthermore, we evaluated the algorithm’s functionality and performance through simulations of swarm intelligence systems under unstable network environments caused by increased latency, network jitter, and data packet loss. Experimental results demonstrate that RCA-SI outperforms Raft, Paxos, and Multi-Paxos in terms of throughput under unstable network conditions, particularly in high-latency and high-packet-loss scenarios. The algorithm’s correctness is formally verified using TLA+, and its efficiency is confirmed through simulations, highlighting its suitability for swarm intelligence systems.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104202"},"PeriodicalIF":7.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144088785","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}
Yong Liu , Bin Xu , Tianyi Yu , Qian Meng , Ben Wang , Yimo Shen
{"title":"ARS: Adaptive routing strategies using AT-GCN for traffic optimization in data center networks","authors":"Yong Liu , Bin Xu , Tianyi Yu , Qian Meng , Ben Wang , Yimo Shen","doi":"10.1016/j.jnca.2025.104214","DOIUrl":"10.1016/j.jnca.2025.104214","url":null,"abstract":"<div><div>As internet services and Internet of Things (IoT) devices rapidly expand, Data Center Networks (DCN) have become essential for supporting online services, cloud computing, and big data analysis. These devices generate massive amounts of data continuously, leading to uneven and sudden network loads that traditional networks struggle to handle. Existing routing strategies often rely on fine-grained routing or current network states, which can result in misjudgments and fail to manage sudden traffic spikes or meet both low-latency and high-bandwidth requirements effectively. To tackle these challenges, we propose a new routing strategy that combines Software-Defined Networking (SDN) with an Attention-based Temporal Graph Convolutional Network (AT-GCN). By predicting future network states using AT-GCN and analyzing traffic characteristics with a Deep Neural Network (DNN), our method offered more precise traffic scheduling. Specifically, we used an improved butterfly optimization algorithm to route mouse flows through low-latency, stable paths, and employ Dijkstra’s algorithm to send elephant flows along paths with the highest predicted bandwidth. This approach effectively reduces latency and increases throughput. Simulation results demonstrate that our method significantly reduces average Flow Completion Time (FCT) by 18.72% to 62.94% compared to existing ECMP, LetFlow, DLBF, ILB and MABC schemes.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104214"},"PeriodicalIF":7.7,"publicationDate":"2025-05-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144088784","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}
{"title":"KLCMD: K_Length Clustering for Miner Detection on the blockchain social networks to increase the information propagation speed","authors":"Elham Abdollahi Abed, Shahriar Lotfi, Jaber Karimpour","doi":"10.1016/j.jnca.2025.104219","DOIUrl":"10.1016/j.jnca.2025.104219","url":null,"abstract":"<div><div>Information propagation speed on blockchain social networks depends on activation of users on social network and blockchain network as well. Many researches have been done to increase information propagation speed on social networks. Most of these methods consist of finding influential nodes by different methods to propagate information by these nodes. Some researches have been done to increase information propagation speed on blockchain network. These methods consist of modifying validation of blocks, compressing blockchain, removing redundant information, using another consensus algorithm and so on, still, there is no proper method to increase information propagation speed on both of blockchain and social network. In this paper K_Length Clustering for Miner Detection has been proposed for this purpose. It comprises of two clustering and miner detection phases for information propagation on blockchain social networks. In this method a new partition-oriented clustering has been proposed to cluster users of the social network then the suitable user as miner has been chosen for each cluster, in contrast existing methods just use the blockchain network features for miner selection process which it can be unfairly. In this method speed of information propagation has been increased on both networks. This method has been compared with other consensus algorithms and partition-oriented clustering methods. Experimental results show that our approach has improved the speed of information propagation on both of them. Speed improvement in compare of consensus methods is minimum 5.97 % and maximum 6.10 %, in compare of clustering methods is minimum 0.8 % and maximum 46.35 %.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104219"},"PeriodicalIF":7.7,"publicationDate":"2025-05-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144116153","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}
{"title":"FDGAT-WTA: A dynamic detection model for web tracking and advertising based on improved graph attention networks","authors":"Yali Yuan , Runke Li , Guang Cheng","doi":"10.1016/j.jnca.2025.104178","DOIUrl":"10.1016/j.jnca.2025.104178","url":null,"abstract":"<div><div>Web tracking and advertising (WTA) have become pervasive on the Internet, presenting significant challenges to user privacy and data security. Although current defense mechanisms, such as filter list based interceptors and machine learning methods, provide a solution, they do not perform well in complex network environments with missing features, and their large size makes both performance and overhead subject to optimization. This paper introduces FDGAT-WTA (Fine-tuning Dynamics GAT for WTA Detection), a dynamic model based on an improved graph attention network, designed for efficient WTA detection. The model constructs network traffic as a Homogeneous Directed Multigraph (HDMG) and modifies the graph attention aggregation strategy, enabling deep feature extraction and dynamic graph extension through transductive and inductive learning methods. The dynamic detection phase leverages pruning techniques to reduce computational load and memory usage. The experimental results show that compared with existing machine learning based WTA detection methods, FDGAT-WTA has improved detection performance by about 5%, reduced model overhead by about 25% under the same data scale , and can adapt to real complex network environments with partially missing features with minimal performance loss, realizing lightweight and efficient dynamic detection.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104178"},"PeriodicalIF":7.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144138662","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}
{"title":"Distributed deep reinforcement learning for independent task offloading in Mobile Edge Computing","authors":"Mohsen Darchini-Tabrizi , Amirhossein Roudgar , Reza Entezari-Maleki , Leonel Sousa","doi":"10.1016/j.jnca.2025.104211","DOIUrl":"10.1016/j.jnca.2025.104211","url":null,"abstract":"<div><div>Mobile Edge Computing (MEC) has been identified as an innovative paradigm to improve the performance and efficiency of mobile applications by offloading computation-intensive tasks to nearby edge servers. However, the effective implementation of task offloading in MEC systems faces challenges due to uncertainty, heterogeneity, and dynamicity. Deep Reinforcement Learning (DRL) provides a powerful approach for devising optimal task offloading policies in complex and uncertain environments. This paper presents a DRL-based task offloading approach using Deep Deterministic Policy Gradient (DDPG) and Distributed Distributional Deep Deterministic Policy Gradient (D4PG) algorithms. The proposed solution establishes a distributed system, where multiple mobile devices act as Reinforcement Learning (RL) agents to optimize their individual performance. To reduce the computational complexity of the neural networks, Gated Recurrent Units (GRU) are used instead of Long Short-Term Memory (LSTM) units to predict the load of edge nodes within the observed state. In addition, a GRU-based sequencing model is introduced to estimate task sizes in specific scenarios where these sizes are unknown. Finally, a novel scheduling algorithm is proposed that outperforms commonly used approaches by leveraging the estimated task sizes to achieve superior performance. Comprehensive simulations were conducted to evaluate the efficacy of the proposed approach, benchmarking it against multiple baseline and state-of-the-art algorithms. Results show significant improvements in terms of average processing delay and task drop rates, thereby confirming the success of the proposed approach.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"240 ","pages":"Article 104211"},"PeriodicalIF":7.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144070316","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}
Bruno Ramos-Cruz , Javier Andreu-Perez , Francisco J. Quesada-Real , Luis Martínez
{"title":"Fuzzychain: An equitable consensus mechanism for blockchain networks","authors":"Bruno Ramos-Cruz , Javier Andreu-Perez , Francisco J. Quesada-Real , Luis Martínez","doi":"10.1016/j.jnca.2025.104204","DOIUrl":"10.1016/j.jnca.2025.104204","url":null,"abstract":"<div><div>Blockchain technology has become a trusted method for establishing secure and transparent transactions through a distributed, encrypted network. The operation of blockchain is governed by consensus algorithms, among which Proof of Stake (PoS) is popular yet has its drawbacks, notably the potential for centralising power in nodes with larger stakes or higher rewards. Our proposed novel solution, Fuzzychain, leverages fuzzy sets to define stake semantics, introducing a degree of softness in validator selection. This approach mitigates rigid threshold-based decision-making by allowing gradual transitions between stake levels, reducing sharp disparities among validators. By incorporating this enhanced stake evaluation, Fuzzychain promotes a more adaptive and distributed selection process, ensuring a fairer and more inclusive blockchain network. A thorough assessment of a real-time multi-agent blockchain system to examine validator selection and reduce inequality, promoting a more equitable distribution of stakes among validators compared to other consensus mechanisms. This fosters a more inclusive selection process and a more equitably distributed network.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104204"},"PeriodicalIF":7.7,"publicationDate":"2025-05-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144098403","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}
{"title":"Multi-objective transit algorithm based on density sorting and cylindrical grid mechanism for layout optimization of wireless sensor networks","authors":"Yu-Xuan Xing, Jie-Sheng Wang, Shi-Hui Zhang, Si-Wen Zhang, Yun-Hao Zhang, Xiao-Fei Sui","doi":"10.1016/j.jnca.2025.104217","DOIUrl":"10.1016/j.jnca.2025.104217","url":null,"abstract":"<div><div>Wireless Sensor Networks (WSNs) are self-organizing distributed network systems composed of numerous sensor nodes. In order to optimize node deployment in WSNs to effectively control energy consumption, improve perception service quality and extend network lifetime, a multi-objective Transit Algorithm (TS) algorithm based on density sorting and cylindrical grid mechanism was proposed for WSN layout optimization. The Multi-Objective Transit Search (MOTS) algorithm enhances the elite non-dominated sorting process by incorporating density sorting and proposing a cylindrical grid filtering mechanism. This mechanism retains the optimal individuals when the regional density is excessively high, ensuring diversity within the population while generating the Pareto solution set, which is beneficial for the development of sparse areas. An additional external archive is used to maintain a uniformly diverse Pareto solution set. Subsequently, the MOTS algorithm was applied to optimize WSN deployment with coverage and waste rate as indicators, tested across ten WSN scenarios. The results were compared with other algorithms, such as MOPSO, MOSO, MOGWO and MSSA. The findings indicate that MOTS can achieve the competitive solutions with superior performance in terms of both inverted generational distance and hypervolume across all ten cases, demonstrating a satisfactory and uniform Pareto front.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"241 ","pages":"Article 104217"},"PeriodicalIF":7.7,"publicationDate":"2025-05-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144131371","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}