Journal of Network and Computer Applications最新文献

{"title":"Distributed enhanced multi-objective evolutionary algorithm based on decomposition for cluster analysis in wireless sensor network","authors":"Anita Panwar,&nbsp;Satyasai Jagannath Nanda","doi":"10.1016/j.jnca.2024.104032","DOIUrl":"10.1016/j.jnca.2024.104032","url":null,"abstract":"<div><p>Conventional clustering algorithms do not recognize patterns and structures with contradicting objectives in large, distributed datasets. Distributed clustering leverages rapid processing capabilities to allow multiple nodes to work together. This paper proposes a Distributed clustering based on Multiobjective Evolutionary Algorithm by Decomposition (D-MOEA/d) to solve various multiobjective optimization problems in wireless sensor networks (WSNs). In MOEA/d, a multiobjective optimization problem decomposes into several scalar optimization subproblems, each focusing on a distinct objective. Each subproblem is expressed as a clustering problem that uses local data to perform distributed clustering. The proposed method has been extended to achieve improved accuracy in less time by using a smaller feature subset with less redundancy. The Distributed Enhanced MOEA/d (DE-MOEA/d) avoids local optima by achieving diversity in the population using fuzzy-based nearest neighbor selection, sparse population initialization, and evolved mutation operator. This integration improves the accuracy of the clustering process at WSN nodes, ensuring the attainment of well-balanced solutions across multiple optimization criteria in the distributed environment. Average Euclidean and total symmetrical deviations are the two cost functions used to minimize while clustering on the MOEA/d framework. Six real-life WSN datasets are used to assess the performance of the proposed technique: (1) the Delhi air pollution dataset, (2) the Canada weather station dataset, (3) the Thames River water quality dataset, (4) the Narragansett Bay water quality dataset, (5) the Cook Agricultural land dataset and 6) Gordon Soil dataset. The simulation results of both proposed algorithms are compared with Multiobjective distributed particle swarm optimization (DMOPSO) and Distributed K-means (DK-Means). The proposed algorithm DE-MOEA/d performs better in terms of the Silhouette index (SI), Dunn index (DI), Davies–Bouldin index (DBI), and Kruskal–Wallis (KW) statistical test.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104032"},"PeriodicalIF":7.7,"publicationDate":"2024-09-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274300","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":"Security risks and countermeasures of adversarial attacks on AI-driven applications in 6G networks: A survey","authors":"Van-Tam Hoang ,&nbsp;Yared Abera Ergu ,&nbsp;Van-Linh Nguyen ,&nbsp;Rong-Guey Chang","doi":"10.1016/j.jnca.2024.104031","DOIUrl":"10.1016/j.jnca.2024.104031","url":null,"abstract":"<div><p>The advent of sixth-generation (6G) networks is expected to start a new era in mobile networks, characterized by unprecedented high demands on dense connectivity, ultra-reliability, low latency, and high throughput. Artificial intelligence (AI) is at the forefront of this progress, optimizing and enabling intelligence for essential 6G functions such as radio resource allocation, slicing, service offloading, and mobility management. However, AI is subject to a wide range of security risks, most notably adversarial attacks. Recent studies, inspired by computer vision and natural language processing, show that adversarial attacks have significantly reduced performance and caused incorrect decisions in wireless communications, jeopardizing the perspective of transforming AI-based 6G core networks. This survey presents a thorough investigation into the landscape of adversarial attacks and defenses in the realm of AI-powered functions within classic wireless networks, open radio access networks (O-RAN), and 6G networks. Two key findings are as follows. First, by leveraging shared wireless networks, attackers can provide noise perturbation or signal sampling for interference, resulting in misclassification in AI-based channel estimation and signal classification. From these basic weaknesses, 6G introduces new threat vectors from AI-based core functionalities, such as malicious agents in federated learning-based service offloading and adversarial attacks on O-RAN near-real-time RIC (xApp). Second, adversarial training, trustworthy mmWave/Terahertz datasets, adversarial anomaly detection, and quantum technologies for adversarial defenses are the most promising strategies for mitigating the negative effects of the attacks. This survey also identifies possible future research topics for adversarial attacks and countermeasures in 6G AI-enabled technologies.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104031"},"PeriodicalIF":7.7,"publicationDate":"2024-09-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274293","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":"An AKA protocol for 5G-assisted D2D communication in Out-of-Coverage scenario","authors":"Ponjit Borgohain,&nbsp;Hiten Choudhury","doi":"10.1016/j.jnca.2024.104025","DOIUrl":"10.1016/j.jnca.2024.104025","url":null,"abstract":"<div><p>5G-assisted Device to Device (D2D) communication can be broadly categorized into three use case scenarios: In Coverage, Relay Coverage, and Out-of Coverage. The main challenge lies in ensuring secure communication in Out-of Coverage scenarios, as in this situation, neither of the two devices is within the 5G network’s coverage area. Although several researchers have developed authentication mechanisms for securing D2D communication, most are unsuitable for Out-of Coverage scenarios. Additionally, many of these mechanisms cannot withstand free-riding attacks due to the absence of a trusted entity. In a 5G cellular network, a trust relationship can be established between a registered device and the home network through mutual authentication whenever the former is within the latter’s coverage area. Leveraging this trust, this paper proposes a lightweight 5G-assisted authentication protocol for mutual authentication between two communicating devices in Out-of Coverage scenarios. The proposed protocol meets the necessary security goals and mitigates various security attacks, including free-riding attacks. The correctness of the proposed protocol is formally established using the Scyther tool and Random Oracle Model. Furthermore, performance analysis shows that the protocol is efficient in terms of computation overhead, communication overhead and energy consumption compared to similar works in the literature. The computation overhead is found to be 596.12 ms for the Requestor device and 587.26 ms for the Requestee device. The communication overhead is 2720 bits and the total energy consumption for both devices combined is found to be 3016.93 millijoules.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104025"},"PeriodicalIF":7.7,"publicationDate":"2024-09-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142230573","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":"Generalized hierarchical coded caching","authors":"Juan Eloy Espozo-Espinoza ,&nbsp;Manuel Fernández-Veiga ,&nbsp;Francisco Troncoso-Pastoriza","doi":"10.1016/j.jnca.2024.104027","DOIUrl":"10.1016/j.jnca.2024.104027","url":null,"abstract":"<div><p>Optimizing data traffic is a key concern in content distribution networks to reduce the bandwidth needed to serve the requested content to the final users. In this context, hierarchical coded caching has been proposed as an effective method for reducing traffic. The typical two-level scenario consists in a tree-like structure: on the first layer, a set of intermediate nodes or helpers with local caches store and serve content to a subset of users at the second layer, who also have their local caches. A central server partially stores its content between the first- and second-layer caches, in uncoded form, and subsequently transmits coded messages to satisfy the files demanded by the users. This topology has been thoroughly analyzed in the literature over the past years; however, little attention has been put in arbitrary topologies, where users might be connected to multiple helper nodes, which is especially interesting for scenarios such as wireless networks. Thus, in this paper we study a hierarchical two-level coded caching system with an arbitrary topology and propose a novel content distribution method for this generalized model that leverages the multiple connections between users and helpers to improve the performance of the distribution process. We give achievability results for this system and compare its performance with other classical single-layer and two-layer coded caching systems. Our results show that further gains are possible by using two levels of caching in different operating regimes.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104027"},"PeriodicalIF":7.7,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236883","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":"SSBM: A spatially separated boxes-based multi-tab website fingerprinting model","authors":"Xueshu Hong ,&nbsp;Xingkong Ma ,&nbsp;Shaoyong Li ,&nbsp;Yiqing Cai ,&nbsp;Bo Liu","doi":"10.1016/j.jnca.2024.104023","DOIUrl":"10.1016/j.jnca.2024.104023","url":null,"abstract":"<div><p>In recent years, the website fingerprinting (WF) attack against the Tor anonymity system has become a hot research issue. The state-of-the-art WF studies have shown that the detection accuracy of websites is up to more than 95%. However, they are mainly conducted under the single-tab assumption, where each sample contains only one website traffic. The single-tab setting could not be realistic because users often open multiple tabs to browse simultaneously. The requests and responses from multiple tabs will overlap and interfere with each other, destroying existing single-tab WF attacks. In addition, the proposed multi-tab WF attack works poorly when traffic overlaps seriously. It remains challenging to implement WF attacks in multi-tab scenarios. This paper investigates a new spatial separated boxes-based multi-tab website fingerprinting model, called SSBM, to solve the multi-tab WF problem. It is an end-to-end model that separates traffic by equal-sized boxes and extracts features with convolutional neural networks. By predicting the label of each box, the tabs of the whole traffic are inferred. We design and implement SSBM and compare it with state-of-the-art multi-tab WF attacks in two different multi-tab modes: overlapping mode and delayed mode. In the overlapping mode, SSBM can successfully identify 81.24% of the first tab and 64.72% of the second tab when the overlapping proportions of the two tabs’ traffic reaches 50%, which are 4% and 29% higher than the current strongest BAPM. In the delayed mode, when the second tab traffic starts to overlap with the first tab traffic with a 5-second delay, SSBM improves the first tab’s classification accuracy from 60% to 69% and the second tab’s detection rates from 33% to 53%. Moreover, SSBM achieves the highest improvement, nearly 40%, in the three-tab evaluations. The experimental results show that SSBM outperforms existing multi-tab WF attack methods.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104023"},"PeriodicalIF":7.7,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236884","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":"Exclusively in-store: Acoustic location authentication for stationary business devices","authors":"Sungbin Park ,&nbsp;Changbae Seo ,&nbsp;Xueqiang Wang ,&nbsp;Yeonjoon Lee ,&nbsp;Seung-Hyun Seo","doi":"10.1016/j.jnca.2024.104028","DOIUrl":"10.1016/j.jnca.2024.104028","url":null,"abstract":"<div><p>Over the past decade, the adoption of Internet of Things (IoT) devices has greatly revolutionized the retail and commerce industries. However, these devices are vulnerable to attacks, such as theft, which raises significant security and privacy concerns for business assets. Securing such business-owned devices is challenging, particularly due to the business contexts that require not only authenticating the devices but also verifying the environment in which the devices are located. In this study, we present a zero-effort authentication approach based on acoustic fingerprints, namely <em>AcousticAuth</em>. <em>AcousticAuth</em> enables a “verifier” device to authenticate and verify the work environment of multiple “prover” devices (e.g., kiosks) by extracting their acoustic fingerprints and direction information. Additionally, we adopt a novel method based on beamforming to expand the fingerprint space of the provers. We implemented a prototype of <em>AcousticAuth</em> using real-world IoT devices, and the evaluation of the prototype indicates that <em>AcousticAuth</em> is highly effective and achieves high sensitivity when authenticating different devices across environments. Our results demonstrate that <em>AcousticAuth</em> can accurately distinguish between different devices and the same model devices with the error rate of 0.03%, significantly enhancing the security of IoT devices in retail settings. <em>AcousticAuth</em> also distinguishes between the different environments with an error rate of 0.00%. Lastly, the system shows robustness against various acoustic interference scenarios, making it a practical solution for dynamic business environments. We not only introduce a novel security mechanism that pushes the limit of fingerprint-based authentication by expanding the fingerprint pool but also provide comprehensive insights into its implementation and performance, paving the way for more secure IoT deployments in the commercial sector.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104028"},"PeriodicalIF":7.7,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142274301","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":"Living on the edge: A survey of Digital Twin-Assisted Task Offloading in safety-critical environments","authors":"Pedro R.X. do Carmo ,&nbsp;Diego de Freitas Bezerra ,&nbsp;Assis T. Oliveira Filho ,&nbsp;Eduardo Freitas ,&nbsp;Miguel L.P.C. Silva ,&nbsp;Marrone Dantas ,&nbsp;Beatriz Oliveira ,&nbsp;Judith Kelner ,&nbsp;Djamel F.H. Sadok ,&nbsp;Ricardo Souza","doi":"10.1016/j.jnca.2024.104024","DOIUrl":"10.1016/j.jnca.2024.104024","url":null,"abstract":"<div><p>This survey delves into the synergy between Digital Twin technology and Task Offloading within safety-critical sectors, offering a nuanced understanding of their integration, potential benefits, and associated challenges. By defining fundamental concepts and exploring real-world implementations, this study evaluates the impact of Digital Twin-Assisted Task Offloading on optimizing resource utilization in safety-critical environments. Central to our analysis is the evaluation of key performance metrics guiding task offloading strategies, notably latency, and energy consumption, which are critical for achieving real-time efficiency and sustainable operations in edge computing environments. The survey further identifies a gap in the literature concerning cybersecurity and privacy concerns, crucial elements given the vulnerability of these systems to cyber threats and data breaches. It also highlights the emerging significance of 6G technology as a pivotal enabler for future advancements. This work not only serves as a valuable resource for professionals and researchers in safety-critical industries but also underscores the importance of addressing cybersecurity measures, advocating for standardized frameworks, and aligning with future technological trends to fully harness the potential of Digital Twin-Assisted Task Offloading.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104024"},"PeriodicalIF":7.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142230793","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 Fog computing system for weapon detection and face recognition","authors":"Héctor Martinez,&nbsp;Francisco J. Rodriguez-Lozano,&nbsp;Fernando León-García,&nbsp;Jose M. Palomares,&nbsp;Joaquín Olivares","doi":"10.1016/j.jnca.2024.104026","DOIUrl":"10.1016/j.jnca.2024.104026","url":null,"abstract":"<div><p>Surveillance systems are very important to prevent situations where armed people appear. To minimize human supervision, there are algorithms based on artificial intelligence that perform a large part of the identification and detection tasks. These systems usually require large data processing servers. However, a high number of cameras causes congestion in the networks due to a large amount of data being sent. This work introduces a novel system for identifying individuals with weapons by leveraging Edge, Fog, and Cloud computing. The key advantages include minimizing the data transmitted to the Cloud and optimizing the computations performed within it. The main benefits of our proposal are the high and simple scalability, the immediacy of the detection, as well as the optimization of processes through distributed processing of high performance in the Fog layer. Moreover, the structure of this proposal is suitable for 5G camera networks, which require low latency and quick responses.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104026"},"PeriodicalIF":7.7,"publicationDate":"2024-09-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236885","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":"A survey on Ethereum pseudonymity: Techniques, challenges, and future directions","authors":"Shivani Jamwal ,&nbsp;José Cano ,&nbsp;Gyu Myoung Lee ,&nbsp;Nguyen H. Tran ,&nbsp;Nguyen Truong","doi":"10.1016/j.jnca.2024.104019","DOIUrl":"10.1016/j.jnca.2024.104019","url":null,"abstract":"<div><p>Blockchain technology has emerged as a transformative force in various sectors, including finance, healthcare, supply chains, and intellectual property management. Beyond Bitcoin’s role as a decentralized payment system, Ethereum represents a notable application of blockchain, featuring Smart Contract functionality that enables the development and execution of decentralized applications (DApps). A key feature of Ethereum, and public blockchains in general, is pseudonymity, typically achieved by using public keys as pseudonyms for users. Despite implementing several privacy-preserving techniques, the public recording of user activities on the blockchain allows various deanonymization methods that can profile users, reveal sensitive information, and potentially re-identify them. Most blockchains, such as Bitcoin, Litecoin, and Cardano, employ the Unspent Transaction Output (UTXO) model for accounting, which focuses on individual transactions and is susceptible to various deanonymization techniques. In contrast, Ethereum uses an account-based transaction model, integrating the concepts of accounts and wallets at the protocol level. This makes most UTXO-based deanonymization techniques ineffective for Ethereum. However, alternative methods with the potential to deanonymize Ethereum users have been proposed and developed. Privacy preservation techniques have been used to counteract deanonymization attempts; however, the challenges related to these techniques, their effectiveness and efficiency, and the trade-off between usability and protection levels remain areas for further exploration. This survey presents a comprehensive analysis of state-of-the-art privacy preservation along with deanonymization techniques in the blockchain and Ethereum ecosystems. This survey examines the intrinsic mechanisms supporting pseudonymity in Ethereum, providing a detailed assessment of the advantages and disadvantages of privacy preservation techniques, and suggests potential countermeasures against those deanonymization methods. It also discusses the implications arising from the intersection of DApps and data protection legislation, which is vital for ensuring the coexistence and advancement of groundbreaking blockchain capabilities and protecting user data.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104019"},"PeriodicalIF":7.7,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142236891","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":"DeCa360: Deadline-aware edge caching for two-tier 360° video streaming","authors":"Tao Lin ,&nbsp;Yang Chen ,&nbsp;Hao Yang ,&nbsp;Yuan Zhang ,&nbsp;Bo Jiang ,&nbsp;Jinyao Yan","doi":"10.1016/j.jnca.2024.104022","DOIUrl":"10.1016/j.jnca.2024.104022","url":null,"abstract":"<div><p>Two-tier 360° video streaming provides a robust solution for handling inaccurate viewport prediction and varying network conditions. Within this paradigm, the client employs a dual-buffer mechanism consisting of a long buffer for panoramic basic-quality segments and a short buffer for high-quality tiles. However, designing an efficient edge caching strategy for two-tier 360° videos is non-trivial. First, as basic-quality segments and high-quality tiles possess different delivery deadlines as well as content popularity, ignoring these discrepancies may result in inefficient edge caching. Second, accurately predicting the popularity of 360° videos at a fine granularity of video segments and tiles remains a challenge. To address these issues, we present DeCa360, a deadline-aware edge caching framework for 360° videos. Specifically, we introduce a lightweight runtime cache partitioning approach to achieve a careful balance between improving the cache hit ratio and guaranteeing more on-time delivery of objects. Moreover, we design a content popularity prediction method for two-tier 360° videos that combines a learning-based prediction model with domain knowledge of video streaming, leading to improved prediction accuracy and efficient cache replacement. Extensive experimental evaluations demonstrate that DeCa360 outperforms all baseline algorithms in terms of byte-hit ratio and on-time delivery ratio, making it a promising approach for efficient edge caching of 360° videos.</p></div>","PeriodicalId":54784,"journal":{"name":"Journal of Network and Computer Applications","volume":"232 ","pages":"Article 104022"},"PeriodicalIF":7.7,"publicationDate":"2024-09-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142166723","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}