Journal of Network and Computer Applications最新文献

DAPNEML: Disease-diet associations prediction in a NEtwork using a machine learning based approach

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-19 DOI: 10.1016/j.jnca.2025.104140

Rashmeet Toor, Inderveer Chana

Generic notions about associations between certain diseases and diets are quite popular, but there are many evidences of other unknown disease-diet associations in literature that need to be fully explored. Such associations are currently being studied by medical researchers through meta-analysis or other prospective studies limiting it to a certain population or area. This study aims to use a combined view of such associations from literature for predicting unknown associations using advanced computational techniques including Network Analysis and Machine Learning. Disease-Diet Associations Prediction in a NEtwork using Machine Learning (DAPNEML) is an approach designed to curate known disease-diet and diet-diet associations data from literature, visualize and integrate the data in the form of a network, extract features from these complex interdependencies using network algorithms and predict unknown associations using machine learning. The predictions are performed in two phases, with the first predicting if an association exists between disease-diet whereas the second predicting the nature of its association (diet is harmful or helpful for a disease). Accuracies achieved in phase 1 and phase 2 are 83% and 76% respectively. The proposed approach can be of great help for researchers and biomedical professionals in constructing diet based disease progressions.

{"title":"DAPNEML: Disease-diet associations prediction in a NEtwork using a machine learning based approach","authors":"Rashmeet Toor, Inderveer Chana","doi":"10.1016/j.jnca.2025.104140","DOIUrl":"10.1016/j.jnca.2025.104140","url":null,"abstract":"<div><div>Generic notions about associations between certain diseases and diets are quite popular, but there are many evidences of other unknown disease-diet associations in literature that need to be fully explored. Such associations are currently being studied by medical researchers through meta-analysis or other prospective studies limiting it to a certain population or area. This study aims to use a combined view of such associations from literature for predicting unknown associations using advanced computational techniques including Network Analysis and Machine Learning. Disease-Diet Associations Prediction in a NEtwork using Machine Learning (DAPNEML) is an approach designed to curate known disease-diet and diet-diet associations data from literature, visualize and integrate the data in the form of a network, extract features from these complex interdependencies using network algorithms and predict unknown associations using machine learning. The predictions are performed in two phases, with the first predicting if an association exists between disease-diet whereas the second predicting the nature of its association (diet is harmful or helpful for a disease). Accuracies achieved in phase 1 and phase 2 are 83% and 76% respectively. The proposed approach can be of great help for researchers and biomedical professionals in constructing diet based disease progressions.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"238 ","pages":"Article 104140"},"PeriodicalIF":7.7,"publicationDate":"2025-02-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143488302","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

A Comprehensive Survey of Smart Contracts Vulnerability Detection Tools: Techniques and Methodologies

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-18 DOI: 10.1016/j.jnca.2025.104142

Niosha Hejazi, Arash Habibi Lashkari

The widespread use of blockchain technology has highlighted smart contracts as crucial components in digital transactions. However, their susceptibility to vulnerabilities poses significant challenges to security and dependability. This survey presents a comprehensive evaluation of 256 smart contracts analysis tools, categorized by methodologies such as fuzzing, machine learning, symbolic execution, and formal verification. Through theoretical and practical assessments, this paper offers insights into the current landscape of smart contracts vulnerability detection tools. Additionally, the paper systematically evaluates selected tools based on real-world datasets. The results show that while many tools perform well, they do not fully cover all vulnerability types accurately, highlighting the need for improved integration of detection methodologies. The findings aim to bridge gaps in existing methods, guiding future improvements for enhancing the security of blockchain applications.

引用次数: 0

MuLPP: A multi-level privacy preserving for blockchain-based bilateral P2P energy trading

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-17 DOI: 10.1016/j.jnca.2025.104141

Juhar Abdella , Zahir Tari , Redowan Mahmud

Challenges pertaining to user anonymity and data privacy are among the major concerns in blockchain-based bilateral Peer-to-Peer Energy Trading (P2P-ET). However, existing solutions focus only on user anonymity and are severely exposed to fake energy offers that can lead to denial-of-service attacks. Moreover, the off-chain communication mechanism used for private energy negotiation is computationally inefficient. This paper proposes a Multi-Level Privacy-Preserving system (MuLPP) for blockchain-based bilateral P2P-ET that provides user anonymity, energy price and energy amount privacy while protecting against fake energy offers. To address the privacy concerns in a comprehensive way, MuLPP offers three levels of privacy: public-level, energy authority-level and participant-level. MuLPP is based on blockchain smart contracts, RSA accumulators, public key aggregation and BLS-based multi-signature to achieve user anonymity, data privacy, robustness against fake energy offers and security in off-chain negotiation. This paper also proposes a permissioned anonymous decentralized P2P off-chain communication protocol, known as PADPeC, to enhance the privacy and performance of off-chain energy negotiations. Experimental results conducted in a real environment indicate that MuLPP provides 75 to 100 times lower on-chain latency. On the other hand, PADPeC reduces the message-sending time and the number of message exchanges in the off-chain communication by a factor of 4123 and 7.88 respectively compared to the existing systems. Formal security verification conducted using AVISPA security verification tool also revealed that the system is secure against various attacks such as sybil, network flooding and fake energy offer attack.

{"title":"MuLPP: A multi-level privacy preserving for blockchain-based bilateral P2P energy trading","authors":"Juhar Abdella , Zahir Tari , Redowan Mahmud","doi":"10.1016/j.jnca.2025.104141","DOIUrl":"10.1016/j.jnca.2025.104141","url":null,"abstract":"<div><div>Challenges pertaining to user anonymity and data privacy are among the major concerns in blockchain-based bilateral Peer-to-Peer Energy Trading (P2P-ET). However, existing solutions focus only on user anonymity and are severely exposed to fake energy offers that can lead to denial-of-service attacks. Moreover, the off-chain communication mechanism used for private energy negotiation is computationally inefficient. This paper proposes a Multi-Level Privacy-Preserving system (MuLPP) for blockchain-based bilateral P2P-ET that provides user anonymity, energy price and energy amount privacy while protecting against fake energy offers. To address the privacy concerns in a comprehensive way, MuLPP offers three levels of privacy: public-level, energy authority-level and participant-level. MuLPP is based on blockchain smart contracts, RSA accumulators, public key aggregation and BLS-based multi-signature to achieve user anonymity, data privacy, robustness against fake energy offers and security in off-chain negotiation. This paper also proposes a permissioned anonymous decentralized P2P off-chain communication protocol, known as PADPeC, to enhance the privacy and performance of off-chain energy negotiations. Experimental results conducted in a real environment indicate that MuLPP provides 75 to 100 times lower on-chain latency. On the other hand, PADPeC reduces the message-sending time and the number of message exchanges in the off-chain communication by a factor of 4123 and 7.88 respectively compared to the existing systems. Formal security verification conducted using AVISPA security verification tool also revealed that the system is secure against various attacks such as sybil, network flooding and fake energy offer attack.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104141"},"PeriodicalIF":7.7,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143453110","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PRISM: PSI and Voronoi diagram based Automated Exposure Notification with location privacy

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-13 DOI: 10.1016/j.jnca.2025.104129

Jiezhen Tang , Hui Zhu , Liqun Chen , Fengwei Wang , Hui Li

Automated Exposure Notification techniques have been developed as pervasive risk assessment tools in public crisis management, particularly for the containment of infectious diseases. However, the widely adopted Bluetooth Low Energy or location-based AEN techniques face challenges in simultaneously providing fined-grained, real-time, and location privacy-preserving detection and notification. Therefore, we propose PRISM, an enhanced and hierarchical AEN scheme, offering both efficiency and security. Specifically, by analyzing the geographic properties of contact tracing in crisis, we first construct a Voronoi diagram map for detailed disaster-related data collection and management. Then, we introduce Hazardous Monitoring for broadcasting disaster information, which enables citizens to conveniently receive updates from public crisis management departments and rapidly recognize potential risks. In addition, we design Secure Exposure Identification, leveraging the Voronoi diagram and homomorphic encryption-based Private Set Intersection (PSI), allowing citizens to securely trace and identify contact with infected individuals. Detailed security analysis confirms that PRISM effectively safeguards citizens against privacy breaches. Finally, a PRISM system is developed and implemented for testing under real-world constraints, with experiment results indicating its efficacy and operational efficiency.

{"title":"PRISM: PSI and Voronoi diagram based Automated Exposure Notification with location privacy","authors":"Jiezhen Tang , Hui Zhu , Liqun Chen , Fengwei Wang , Hui Li","doi":"10.1016/j.jnca.2025.104129","DOIUrl":"10.1016/j.jnca.2025.104129","url":null,"abstract":"<div><div>Automated Exposure Notification techniques have been developed as pervasive risk assessment tools in public crisis management, particularly for the containment of infectious diseases. However, the widely adopted Bluetooth Low Energy or location-based AEN techniques face challenges in simultaneously providing fined-grained, real-time, and location privacy-preserving detection and notification. Therefore, we propose PRISM, an enhanced and hierarchical AEN scheme, offering both efficiency and security. Specifically, by analyzing the geographic properties of contact tracing in crisis, we first construct a Voronoi diagram map for detailed disaster-related data collection and management. Then, we introduce Hazardous Monitoring for broadcasting disaster information, which enables citizens to conveniently receive updates from public crisis management departments and rapidly recognize potential risks. In addition, we design Secure Exposure Identification, leveraging the Voronoi diagram and homomorphic encryption-based Private Set Intersection (PSI), allowing citizens to securely trace and identify contact with infected individuals. Detailed security analysis confirms that PRISM effectively safeguards citizens against privacy breaches. Finally, a PRISM system is developed and implemented for testing under real-world constraints, with experiment results indicating its efficacy and operational efficiency.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104129"},"PeriodicalIF":7.7,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143463644","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

Efficient fault tolerance and diagnosis mechanism for Network-on-Chips

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-11 DOI: 10.1016/j.jnca.2025.104133

Mengjie Lv, Hui Dong, Weibei Fan

The Network-on-Chip (NoC) integrates all components within a System-on-Chip (SoC), positioning itself as the SoC’s most critical element. The interconnection network, which forms the foundational topology of the NoC, significantly impacts its performance. As network scale and complexity increase, the inevitability of faults emerges, underscoring the crucial need for robust fault tolerance. In this paper, we introduce a novel conditional fault model, the partial block fault (PBF) model, aimed at enhancing network fault tolerance. This model addresses the distribution of faulty node and guarantees that, even after their removal, the remaining networks maintain normal communication. Leveraging this model, we examine the fault-tolerant capability of

k

-ary

m

-cube networks

Q_{m}^{k}

and provide a theoretical analysis demonstrating the network’s connectivity. We then present an

O (N log N)

algorithm, named DIAG-PBF, designed to ascertain the status of nodes in

Q_{m}^{k}

while allowing for the sacrifice of some fault-free nodes, where

N

represents the total number of nodes in

Q_{m}^{k}

. Performance analysis indicates that our fault tolerance results surpass previously known benchmarks. Additionally, experimental evaluations reveal that our approach supports a low transmission failure rate, further validating its efficacy.

{"title":"Efficient fault tolerance and diagnosis mechanism for Network-on-Chips","authors":"Mengjie Lv, Hui Dong, Weibei Fan","doi":"10.1016/j.jnca.2025.104133","DOIUrl":"10.1016/j.jnca.2025.104133","url":null,"abstract":"<div><div>The Network-on-Chip (NoC) integrates all components within a System-on-Chip (SoC), positioning itself as the SoC’s most critical element. The interconnection network, which forms the foundational topology of the NoC, significantly impacts its performance. As network scale and complexity increase, the inevitability of faults emerges, underscoring the crucial need for robust fault tolerance. In this paper, we introduce a novel conditional fault model, the partial block fault (PBF) model, aimed at enhancing network fault tolerance. This model addresses the distribution of faulty node and guarantees that, even after their removal, the remaining networks maintain normal communication. Leveraging this model, we examine the fault-tolerant capability of <span><math><mi>k</mi></math></span>-ary <span><math><mi>m</mi></math></span>-cube networks <span><math><msubsup><mrow><mi>Q</mi></mrow><mrow><mi>m</mi></mrow><mrow><mi>k</mi></mrow></msubsup></math></span> and provide a theoretical analysis demonstrating the network’s connectivity. We then present an <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mi>N</mi><mo>log</mo><mi>N</mi><mo>)</mo></mrow></mrow></math></span> algorithm, named DIAG-PBF, designed to ascertain the status of nodes in <span><math><msubsup><mrow><mi>Q</mi></mrow><mrow><mi>m</mi></mrow><mrow><mi>k</mi></mrow></msubsup></math></span> while allowing for the sacrifice of some fault-free nodes, where <span><math><mi>N</mi></math></span> represents the total number of nodes in <span><math><msubsup><mrow><mi>Q</mi></mrow><mrow><mi>m</mi></mrow><mrow><mi>k</mi></mrow></msubsup></math></span>. Performance analysis indicates that our fault tolerance results surpass previously known benchmarks. Additionally, experimental evaluations reveal that our approach supports a low transmission failure rate, further validating its efficacy.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104133"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395511","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

BAS-NDN: BlockChain based mobile producer authentication scheme for Named Data Networking

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-11 DOI: 10.1016/j.jnca.2025.104135

Guangquan Xu , Chenghe Dong , Cong Wang , Feng Feng

Named Data Network (NDN) is a content-centric, name-based communication architecture, with a push-based communication model naturally supports consumer mobility. However, the management of producer prefix authentication during mobility is challenging due to NDN’s name-based mechanism, which facilitates direct interaction between producers and the forwarding plane. The current solutions fail to balance security and efficiency. To address insecure interactions arising from producer mobility, we introduce a protocol for blockchain-based mobile producer authentication (BAS-NDN). Our protocol relies on a novel elliptic curve-based certificateless signcryption scheme, which is easy to deploy, provides both signature and encryption, and avoids complex certificate management and key escrow problems. This makes it suitable for secure and efficient mobile management in NDN. In addition, the proposed scheme efficiently authenticates the producer’s prefixes by enforcing the producer to publish routing updates that use only valid prefixes. This design renders it resistant to prefix hijacking attacks. Through analyzing under the random oracle model, it is also resistant to both Type I and Type II adversaries present in certificateless signcryption. Finally, experimental analysis indicates that our scheme provides significant performance benefits.

命名数据网络（NDN）是一种以内容为中心、基于名称的通信架构，其基于推送的通信模式自然支持消费者的移动性。然而，由于 NDN 基于名称的机制有利于生产者和转发平面之间的直接交互，因此在移动过程中管理生产者前缀认证具有挑战性。目前的解决方案无法在安全性和效率之间取得平衡。为了解决生产者移动性带来的不安全交互问题，我们推出了基于区块链的移动生产者认证协议（BAS-NDN）。我们的协议依赖于一种新颖的基于椭圆曲线的无证书签名加密方案，该方案易于部署，既能提供签名又能提供加密，还能避免复杂的证书管理和密钥托管问题。这使它适用于 NDN 中安全高效的移动管理。此外，建议的方案通过强制生产者发布只使用有效前缀的路由更新，有效地验证了生产者的前缀。这种设计使其能够抵御前缀劫持攻击。通过在随机甲骨文模型下进行分析，它还能抵御无证书签名加密中存在的第一类和第二类对手。最后，实验分析表明，我们的方案具有显著的性能优势。

{"title":"BAS-NDN: BlockChain based mobile producer authentication scheme for Named Data Networking","authors":"Guangquan Xu , Chenghe Dong , Cong Wang , Feng Feng","doi":"10.1016/j.jnca.2025.104135","DOIUrl":"10.1016/j.jnca.2025.104135","url":null,"abstract":"<div><div>Named Data Network (NDN) is a content-centric, name-based communication architecture, with a push-based communication model naturally supports consumer mobility. However, the management of producer prefix authentication during mobility is challenging due to NDN’s name-based mechanism, which facilitates direct interaction between producers and the forwarding plane. The current solutions fail to balance security and efficiency. To address insecure interactions arising from producer mobility, we introduce a protocol for blockchain-based mobile producer authentication (BAS-NDN). Our protocol relies on a novel elliptic curve-based certificateless signcryption scheme, which is easy to deploy, provides both signature and encryption, and avoids complex certificate management and key escrow problems. This makes it suitable for secure and efficient mobile management in NDN. In addition, the proposed scheme efficiently authenticates the producer’s prefixes by enforcing the producer to publish routing updates that use only valid prefixes. This design renders it resistant to prefix hijacking attacks. Through analyzing under the random oracle model, it is also resistant to both Type I and Type II adversaries present in certificateless signcryption. Finally, experimental analysis indicates that our scheme provides significant performance benefits.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104135"},"PeriodicalIF":7.7,"publicationDate":"2025-02-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143420070","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

Optimizing cloud resource management with an IoT-enabled optimized virtual machine migration scheme for improved efficiency

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-10 DOI: 10.1016/j.jnca.2025.104137

Chunjing Liu, Lixiang Ma, Minfeng Zhang, Haiyan Long

Cloud computing manages many resources and alterations to meet the demands made by consumers at multiple locations and in numerous applications. Cloud computing presents a significant obstacle to efficient resource usage and balance of loads due to the dynamic nature of consumer requirements and tasks. The inflexibility of conventional methods guarantees inadequate outcomes and waste of resources. Motivated by improved cloud infrastructure management, the present research introduces a novel approach to load optimization and migrating Virtual Machines (VMs) based on agents modelled and Internet of Things (IoT) devices. This research aims to boost cloud performance primarily by optimizing the utilization of resources and distribution of workloads. Hence, a novel approach, the Optimized Virtual Machine Migration Scheme (OVMMS), is introduced that uses the Squirrel Search Algorithm (SSA) for migrating VMs. By emulating squirrel behaviour during migration and search, these agents maximize load balance and the distribution of resources. During the analysis, IoT devices were enabled to monitor and control cloud resources to minimize wastage. Results from experimental analysis demonstrate that the proposed strategy outperforms the state-of-the-art in numerous key areas, including service dissemination, load mitigation, managing failures, mitigating time, and endurance of VM. The results show that the number of failures and the time it takes to mitigate them have dropped dramatically, while services' efficiency and distribution rates have improved substantially. The results illustrate that the squirrel-driven approach holds significant potential for addressing vital issues in cloud computing scenarios. This method asserts that optimizing the distribution of resources and the allocation of workloads may improve systems adaptability, service dependability, and cloud infrastructure operations. The proposed scheme maximizes load mitigation by 11.59%, service dissemination by 8.1%, and VM availability by 8.56%, reducing failures by 12.12% for the maximum service providers.

{"title":"Optimizing cloud resource management with an IoT-enabled optimized virtual machine migration scheme for improved efficiency","authors":"Chunjing Liu, Lixiang Ma, Minfeng Zhang, Haiyan Long","doi":"10.1016/j.jnca.2025.104137","DOIUrl":"10.1016/j.jnca.2025.104137","url":null,"abstract":"<div><div>Cloud computing manages many resources and alterations to meet the demands made by consumers at multiple locations and in numerous applications. Cloud computing presents a significant obstacle to efficient resource usage and balance of loads due to the dynamic nature of consumer requirements and tasks. The inflexibility of conventional methods guarantees inadequate outcomes and waste of resources. Motivated by improved cloud infrastructure management, the present research introduces a novel approach to load optimization and migrating Virtual Machines (VMs) based on agents modelled and Internet of Things (IoT) devices. This research aims to boost cloud performance primarily by optimizing the utilization of resources and distribution of workloads. Hence, a novel approach, the Optimized Virtual Machine Migration Scheme (OVMMS), is introduced that uses the Squirrel Search Algorithm (SSA) for migrating VMs. By emulating squirrel behaviour during migration and search, these agents maximize load balance and the distribution of resources. During the analysis, IoT devices were enabled to monitor and control cloud resources to minimize wastage. Results from experimental analysis demonstrate that the proposed strategy outperforms the state-of-the-art in numerous key areas, including service dissemination, load mitigation, managing failures, mitigating time, and endurance of VM. The results show that the number of failures and the time it takes to mitigate them have dropped dramatically, while services' efficiency and distribution rates have improved substantially. The results illustrate that the squirrel-driven approach holds significant potential for addressing vital issues in cloud computing scenarios. This method asserts that optimizing the distribution of resources and the allocation of workloads may improve systems adaptability, service dependability, and cloud infrastructure operations. The proposed scheme maximizes load mitigation by 11.59%, service dissemination by 8.1%, and VM availability by 8.56%, reducing failures by 12.12% for the maximum service providers.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104137"},"PeriodicalIF":7.7,"publicationDate":"2025-02-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143430024","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

TPMCD: A method to optimizing cost and throughput for clustering tasks and hybrid containers in the cloud data center

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-08 DOI: 10.1016/j.jnca.2025.104132

Arash GhorbanniaDelavar

The regulatory of task classification or clustering and hybrid containers in cloud data centers has a lower overhead of cost compared to virtual machines, also it has a direct impact on the load balance, accessibility of virtual machines, and increase of efficiency. Therefore, additional resources with high computing power usage are one of the important issues. In the proposed method merging the index parameters of response time, execution accuracy and their sensitivity rate have been used. In TPMCD(ThroughPut and cost optimizing Method for Clustering tasks and hybrid containers in the cloud Data center), customers agreement, as a service and performance of the connection, the efficiency of service quality and reliability of algorithms, requests, and confirmations (short, medium, long) due to the configuration of resources and containers and the intelligent detector threshold, protection of the increase in system efficiency and energy consumption decrease synchronously against dynamic workloads and changes in user requests. Classification and re-clustering of tasks in the algorithm have led to an improvement in the real execution time compared to the execution time of the studied algorithms. In the proposed method, by correctly allocating resources for scoring unbalanced data for allocating resources and applications and communicating between containers. In TPMCD, parameters of weight, size, and scoring are used in assigning tasks to processing resources. Confidence interval has been done in proposed method due to the possibility of a small difference in scheduling between different virtual machines. In the TPMCD algorithm, choosing the right VM and reducing the critical points, in the hosts where the load imbalance is created, the load balance is optimized by considering the sensitivity rate and scoring the average tasks. TPMCD method have optimized time and cost by decreasing redundancy. From the obtained results in the evaluation, this method performed better than other ones 7% in cost, 4% in throughput, and 9.5% in real execution time on average simultaneously. Finally, the proposed approach was 3% better than the KC method in the number of nodes used.

{"title":"TPMCD: A method to optimizing cost and throughput for clustering tasks and hybrid containers in the cloud data center","authors":"Arash GhorbanniaDelavar","doi":"10.1016/j.jnca.2025.104132","DOIUrl":"10.1016/j.jnca.2025.104132","url":null,"abstract":"<div><div>The regulatory of task classification or clustering and hybrid containers in cloud data centers has a lower overhead of cost compared to virtual machines, also it has a direct impact on the load balance, accessibility of virtual machines, and increase of efficiency. Therefore, additional resources with high computing power usage are one of the important issues. In the proposed method merging the index parameters of response time, execution accuracy and their sensitivity rate have been used. In TPMCD(ThroughPut and cost optimizing Method for Clustering tasks and hybrid containers in the cloud Data center), customers agreement, as a service and performance of the connection, the efficiency of service quality and reliability of algorithms, requests, and confirmations (short, medium, long) due to the configuration of resources and containers and the intelligent detector threshold, protection of the increase in system efficiency and energy consumption decrease synchronously against dynamic workloads and changes in user requests. Classification and re-clustering of tasks in the algorithm have led to an improvement in the real execution time compared to the execution time of the studied algorithms. In the proposed method, by correctly allocating resources for scoring unbalanced data for allocating resources and applications and communicating between containers. In TPMCD, parameters of weight, size, and scoring are used in assigning tasks to processing resources. Confidence interval has been done in proposed method due to the possibility of a small difference in scheduling between different virtual machines. In the TPMCD algorithm, choosing the right VM and reducing the critical points, in the hosts where the load imbalance is created, the load balance is optimized by considering the sensitivity rate and scoring the average tasks. TPMCD method have optimized time and cost by decreasing redundancy. From the obtained results in the evaluation, this method performed better than other ones 7% in cost, 4% in throughput, and 9.5% in real execution time on average simultaneously. Finally, the proposed approach was 3% better than the KC method in the number of nodes used.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104132"},"PeriodicalIF":7.7,"publicationDate":"2025-02-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378841","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

Lurking in the shadows: Unsupervised decoding of beaconing communication for enhanced cyber threat hunting

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-07 DOI: 10.1016/j.jnca.2025.104127

Arash Mahboubi , Khanh Luong , Geoff Jarrad , Seyit Camtepe , Michael Bewong , Mohammed Bahutair , Ganna Pogrebna

The escalating prevalence of Advanced Persistent Threats (APTs) necessitates the development of more robust solutions capable of effectively thwarting these attacks by monitoring system activities across individual hosts. Existing cloud-native security applications utilize a combination of rule-based and machine learning-based detection techniques to protect digital assets. However, these approaches have limitations. Rule-based detection depends on predefined rules to identify specific attack patterns. Persistent attackers can often evade detection by carefully ensuring that their behavior circumvents these rules. In contrast, machine learning-based detection techniques, which learn attack patterns from data, rely heavily on the availability of labeled data for training. However, labeled data is often unavailable and can be labor-intensive and costly to obtain. In this paper, we address the challenge of detecting APT attacks more holistically by leveraging attackers’ behavior during communication with Command and Control (C2) servers, a critical phase observed in most APT attacks. We aim to reduce false positive alerts for threat hunters by analyzing system network logs to detect potential network beaconing, a common attribute of various malware. We introduce a novel hybrid approach, called NetSpectra Sentinel, which employs a Continuous Time Hidden Markov Model (CT-HMM) to detect hidden states underlying observed patterns within the network logs and Time Series Decomposition (TSD) to model temporal patterns. We evaluate the effectiveness of our approach using 14 benchmark datasets and one synthetic dataset, comparing our method with other state-of-the-art statistical-based and botnet detection techniques. The results demonstrate that our technique achieves significantly higher accuracy in most cases, and even when existing techniques fail, our approach can still detect beaconing post-initial compromise with up to 90% accuracy. Additionally, we achieve up to four times better performance in terms of precision compared to existing statistical-based techniques.

{"title":"Lurking in the shadows: Unsupervised decoding of beaconing communication for enhanced cyber threat hunting","authors":"Arash Mahboubi , Khanh Luong , Geoff Jarrad , Seyit Camtepe , Michael Bewong , Mohammed Bahutair , Ganna Pogrebna","doi":"10.1016/j.jnca.2025.104127","DOIUrl":"10.1016/j.jnca.2025.104127","url":null,"abstract":"<div><div>The escalating prevalence of Advanced Persistent Threats (APTs) necessitates the development of more robust solutions capable of effectively thwarting these attacks by monitoring system activities across individual hosts. Existing cloud-native security applications utilize a combination of rule-based and machine learning-based detection techniques to protect digital assets. However, these approaches have limitations. Rule-based detection depends on predefined rules to identify specific attack patterns. Persistent attackers can often evade detection by carefully ensuring that their behavior circumvents these rules. In contrast, machine learning-based detection techniques, which learn attack patterns from data, rely heavily on the availability of labeled data for training. However, labeled data is often unavailable and can be labor-intensive and costly to obtain. In this paper, we address the challenge of detecting APT attacks more holistically by leveraging attackers’ behavior during communication with Command and Control (C2) servers, a critical phase observed in most APT attacks. We aim to reduce false positive alerts for threat hunters by analyzing system network logs to detect potential network beaconing, a common attribute of various malware. We introduce a novel hybrid approach, called <em><strong>NetSpectra Sentinel</strong></em>, which employs a Continuous Time Hidden Markov Model (CT-HMM) to detect hidden states underlying observed patterns within the network logs and Time Series Decomposition (TSD) to model temporal patterns. We evaluate the effectiveness of our approach using 14 benchmark datasets and one synthetic dataset, comparing our method with other state-of-the-art statistical-based and botnet detection techniques. The results demonstrate that our technique achieves significantly higher accuracy in most cases, and even when existing techniques fail, our approach can still detect beaconing post-initial compromise with up to 90% accuracy. Additionally, we achieve up to four times better performance in terms of precision compared to existing statistical-based techniques.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"236 ","pages":"Article 104127"},"PeriodicalIF":7.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143377185","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Security and privacy of industrial big data: Motivation, opportunities, and challenges

IF 7.7 2区计算机科学 Q1 COMPUTER SCIENCE, HARDWARE & ARCHITECTURE

Journal of Network and Computer Applications

Pub Date : 2025-02-07 DOI: 10.1016/j.jnca.2025.104130

Naveed Anjum , Zohaib Latif , Hongsong Chen

With the rapid growth of the Industrial Internet of Things (IIoT), an abundance of data is generated, and various data acquisition, analytics, and storage mechanisms are developed intelligently for smart industrial productions. Big heterogeneous data of IIoT suffers from security and privacy issues, which are the main hurdles for smooth industrial operations and pose a serious concern to the widespread adoption of IIoT. The existing studies suffer from security loopholes and privacy-preserved solutions for industrial data in a distributed environment. However, emerging technologies like Blockchain, Federated Learning (FL), and Sixth Generation (6G) are potential candidates to provide reliability, security, and privacy in IIoT networks. The blockchain offers the temper proof of security due to its distributive absolute nature. The FL does not share data with the centralized system for training purposes, which ensures data privacy. Finally, 6G communication is used for faster data acquisition and low latency in the mobility-based distributed nature of industrial big data.

In this survey, we present an in-depth analysis of these emerging technologies in IIoT, their motivations, various IIoT applications, current challenges, and future directions regarding industrial big data security and privacy. In addition, an exhaustive investigation of privacy and security threats in industrial big data (acquisition, analytics, and storage) is considered. To this end, various industrial applications, software tools for big data, blockchain, FL, and 6G, as well as a proof of concept for anomaly detection on time-series data, are provided in detail. Lastly, this study aims to provide research challenges and future directions in industrial applications to achieve big data security and privacy.

{"title":"Security and privacy of industrial big data: Motivation, opportunities, and challenges","authors":"Naveed Anjum , Zohaib Latif , Hongsong Chen","doi":"10.1016/j.jnca.2025.104130","DOIUrl":"10.1016/j.jnca.2025.104130","url":null,"abstract":"<div><div>With the rapid growth of the Industrial Internet of Things (IIoT), an abundance of data is generated, and various data acquisition, analytics, and storage mechanisms are developed intelligently for smart industrial productions. Big heterogeneous data of IIoT suffers from security and privacy issues, which are the main hurdles for smooth industrial operations and pose a serious concern to the widespread adoption of IIoT. The existing studies suffer from security loopholes and privacy-preserved solutions for industrial data in a distributed environment. However, emerging technologies like Blockchain, Federated Learning (FL), and Sixth Generation (6G) are potential candidates to provide reliability, security, and privacy in IIoT networks. The blockchain offers the temper proof of security due to its distributive absolute nature. The FL does not share data with the centralized system for training purposes, which ensures data privacy. Finally, 6G communication is used for faster data acquisition and low latency in the mobility-based distributed nature of industrial big data.</div><div>In this survey, we present an in-depth analysis of these emerging technologies in IIoT, their motivations, various IIoT applications, current challenges, and future directions regarding industrial big data security and privacy. In addition, an exhaustive investigation of privacy and security threats in industrial big data (acquisition, analytics, and storage) is considered. To this end, various industrial applications, software tools for big data, blockchain, FL, and 6G, as well as a proof of concept for anomaly detection on time-series data, are provided in detail. Lastly, this study aims to provide research challenges and future directions in industrial applications to achieve big data security and privacy.</div></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"237 ","pages":"Article 104130"},"PeriodicalIF":7.7,"publicationDate":"2025-02-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143378840","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