Massive amounts of data drive the performance of deep learning models, but in practice, data resources are often highly dispersed and bound by data privacy and security concerns, making it difficult for multiple data sources to share their local data directly. Data resources are difficult to aggregate effectively, resulting in a lack of support for model training. How to collaborate between data sources in order to aggregate the value of data resources is therefore an important research question. However, existing distributed-collaborative-learning architectures still face serious challenges in collaborating between nodes that lack mutual trust, with security and trust issues seriously affecting the confidence and willingness of data sources to participate in collaboration. Blockchain technology provides trusted distributed storage and computing, and combining it with collaboration between data sources to build trusted distributed-collaborative-learning architectures is an extremely valuable research direction for application. We propose a trusted distributed-collaborative-learning mechanism based on blockchain smart contracts. Firstly, the mechanism uses blockchain smart contracts to define and encapsulate collaborative behaviours, relationships and norms between distributed collaborative nodes. Secondly, we propose a model-fusion method based on feature fusion, which replaces the direct sharing of local data resources with distributed-model collaborative training and organises distributed data resources for distributed collaboration to improve model performance. Finally, in order to verify the trustworthiness and usability of the proposed mechanism, on the one hand, we implement formal modelling and verification of the smart contract by using Coloured Petri Net and prove that the mechanism satisfies the expected trustworthiness properties by verifying the formal model of the smart contract associated with the mechanism. On the other hand, the model-fusion method based on feature fusion is evaluated in different datasets and collaboration scenarios, while a typical collaborative-learning case is implemented for a comprehensive analysis and validation of the mechanism. The experimental results show that the proposed mechanism can provide a trusted and fair collaboration infrastructure for distributed-collaboration nodes that lack mutual trust and organise decentralised data resources for collaborative model training to develop effective global models.
海量数据驱动着深度学习模型的性能，但在实际应用中，数据资源往往高度分散，且受到数据隐私和安全问题的限制，多个数据源很难直接共享本地数据。数据资源难以有效聚合，导致模型训练缺乏支持。因此，如何在数据源之间进行协作，以聚合数据资源的价值是一个重要的研究问题。然而，现有的分布式协作学习架构在缺乏互信的节点之间开展协作仍面临严峻挑战，安全和信任问题严重影响了数据源参与协作的信心和意愿。区块链技术提供了可信的分布式存储和计算，将其与数据源之间的协作相结合，构建可信的分布式协作学习架构是一个极具应用价值的研究方向。我们提出了一种基于区块链智能合约的可信分布式协作学习机制。首先，该机制使用区块链智能合约来定义和封装分布式协作节点之间的协作行为、关系和规范。其次，我们提出了一种基于特征融合的模型融合方法，用分布式模型协同训练替代本地数据资源的直接共享，组织分布式数据资源进行分布式协作，提高模型性能。最后，为了验证所提机制的可信性和可用性，一方面，我们利用彩色 Petri 网实现了智能合约的形式化建模和验证，并通过验证与该机制相关的智能合约的形式化模型，证明该机制满足预期的可信性属性。另一方面，基于特征融合的模型融合方法在不同的数据集和协作场景中进行了评估，同时实现了一个典型的协作学习案例，对该机制进行了全面的分析和验证。实验结果表明，所提出的机制可以为缺乏互信的分布式协作节点提供可信、公平的协作基础设施，并组织分散的数据资源进行协作模型训练，从而开发出有效的全局模型。
{"title":"TDLearning: Trusted Distributed Collaborative Learning Based on Blockchain Smart Contracts","authors":"Jing Liu, Xuesong Hai, Keqin Li","doi":"10.3390/fi16010006","DOIUrl":"https://doi.org/10.3390/fi16010006","url":null,"abstract":"Massive amounts of data drive the performance of deep learning models, but in practice, data resources are often highly dispersed and bound by data privacy and security concerns, making it difficult for multiple data sources to share their local data directly. Data resources are difficult to aggregate effectively, resulting in a lack of support for model training. How to collaborate between data sources in order to aggregate the value of data resources is therefore an important research question. However, existing distributed-collaborative-learning architectures still face serious challenges in collaborating between nodes that lack mutual trust, with security and trust issues seriously affecting the confidence and willingness of data sources to participate in collaboration. Blockchain technology provides trusted distributed storage and computing, and combining it with collaboration between data sources to build trusted distributed-collaborative-learning architectures is an extremely valuable research direction for application. We propose a trusted distributed-collaborative-learning mechanism based on blockchain smart contracts. Firstly, the mechanism uses blockchain smart contracts to define and encapsulate collaborative behaviours, relationships and norms between distributed collaborative nodes. Secondly, we propose a model-fusion method based on feature fusion, which replaces the direct sharing of local data resources with distributed-model collaborative training and organises distributed data resources for distributed collaboration to improve model performance. Finally, in order to verify the trustworthiness and usability of the proposed mechanism, on the one hand, we implement formal modelling and verification of the smart contract by using Coloured Petri Net and prove that the mechanism satisfies the expected trustworthiness properties by verifying the formal model of the smart contract associated with the mechanism. On the other hand, the model-fusion method based on feature fusion is evaluated in different datasets and collaboration scenarios, while a typical collaborative-learning case is implemented for a comprehensive analysis and validation of the mechanism. The experimental results show that the proposed mechanism can provide a trusted and fair collaboration infrastructure for distributed-collaboration nodes that lack mutual trust and organise decentralised data resources for collaborative model training to develop effective global models.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"47 1 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139159238","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ryunosuke Masaoka, G. Tran, Jin Nakazato, Kei Sakaguchi
Nowadays, wireless communications are ubiquitously available. However, as pervasive as this technology is, there are distinct situations, such as during substantial public events, catastrophic disasters, or unexpected malfunctions of base stations (BSs), where the reliability of these communications might be jeopardized. Such scenarios highlight the vulnerabilities inherent in our current infrastructure. As a result, there is growing interest in establishing temporary networks that offer high-capacity communications and can adaptively shift service locations. To address this gap, this paper investigates the promising avenue of merging two powerful technologies: Unmanned Aerial Vehicles (UAVs) and millimeter-wave (mmWave) transmissions. UAVs, with their ability to be operated remotely and to take flight without being constrained by terrestrial limitations, present a compelling case for being the cellular BSs of the future. When integrated with the high-speed data transfer capabilities of mmWave technology, the potential is boundless. We embark on a hands-on approach to provide a tangible foundation for our hypothesis. We carry out comprehensive experiments using an actual UAV equipped with an mmWave device. Our main objective is to meticulously study its radio wave propagation attributes when the UAVs are in flight mode. The insights gleaned from this hands-on experimentation are profound. We contrast our experimental findings with a rigorous numerical analysis to refine our understanding. This comparative study aimed to shed light on the intricacies of wave propagation behaviors within the vast expanse of the atmosphere.
{"title":"The Future of Flying Base Stations: Empirical and Numerical Investigations of mmWave-Enabled UAVs","authors":"Ryunosuke Masaoka, G. Tran, Jin Nakazato, Kei Sakaguchi","doi":"10.3390/fi16010005","DOIUrl":"https://doi.org/10.3390/fi16010005","url":null,"abstract":"Nowadays, wireless communications are ubiquitously available. However, as pervasive as this technology is, there are distinct situations, such as during substantial public events, catastrophic disasters, or unexpected malfunctions of base stations (BSs), where the reliability of these communications might be jeopardized. Such scenarios highlight the vulnerabilities inherent in our current infrastructure. As a result, there is growing interest in establishing temporary networks that offer high-capacity communications and can adaptively shift service locations. To address this gap, this paper investigates the promising avenue of merging two powerful technologies: Unmanned Aerial Vehicles (UAVs) and millimeter-wave (mmWave) transmissions. UAVs, with their ability to be operated remotely and to take flight without being constrained by terrestrial limitations, present a compelling case for being the cellular BSs of the future. When integrated with the high-speed data transfer capabilities of mmWave technology, the potential is boundless. We embark on a hands-on approach to provide a tangible foundation for our hypothesis. We carry out comprehensive experiments using an actual UAV equipped with an mmWave device. Our main objective is to meticulously study its radio wave propagation attributes when the UAVs are in flight mode. The insights gleaned from this hands-on experimentation are profound. We contrast our experimental findings with a rigorous numerical analysis to refine our understanding. This comparative study aimed to shed light on the intricacies of wave propagation behaviors within the vast expanse of the atmosphere.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"45 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139159191","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
After the introduction of the ChatGPT conversational artificial intelligence (CAI) tool in November 2022, there has been a rapidly growing interest in the use of such tools in higher education. While the educational uses of some other information technology (IT) tools (including collaboration and communication tools, learning management systems, chatbots, and videoconferencing tools) have been frequently evaluated regarding technology acceptance and usability attributes of those technologies, similar evaluations of CAI tools and services like ChatGPT, Bing Chat, and Bard have only recently started to appear in the scholarly literature. In our study, we present a newly developed set of assessment scales that are related to the usability and user experiences of CAI tools when used by university students, as well as the results of evaluation of these assessment scales specifically regarding the CAI Bing Chat tool (i.e., Microsoft Copilot). The following scales were developed and evaluated using a convenience sample (N = 126) of higher education students: Perceived Usefulness, General Usability, Learnability, System Reliability, Visual Design and Navigation, Information Quality, Information Display, Cognitive Involvement, Design Appeal, Trust, Personification, Risk Perception, and Intention to Use. For most of the aforementioned scales, internal consistency (Cronbach alpha) was in the range from satisfactory to good, which implies their potential usefulness for further studies of related attributes of CAI tools. A stepwise linear regression revealed that the most influential predictors of Intention to Use Bing Chat (or ChatGPT) in the future were the usability variable Perceived Usefulness and two user experience variables—Trust and Design Appeal. Also, our study revealed that students’ perceptions of various specific usability and user experience characteristics of Bing Chat were predominantly positive. The evaluated assessment scales could be beneficial in further research that would include other CAI tools like ChatGPT/GPT-4 and Bard.
自 2022 年 11 月推出 ChatGPT 对话式人工智能（CAI）工具后，人们对在高等教育中使用此类工具的兴趣迅速增长。虽然其他一些信息技术（IT）工具（包括协作和交流工具、学习管理系统、聊天机器人和视频会议工具）的教育用途经常被评估，涉及这些技术的技术接受度和可用性属性，但对 ChatGPT、必应聊天和巴德等 CAI 工具和服务的类似评估最近才开始出现在学术文献中。在我们的研究中，我们介绍了一套新开发的与大学生使用 CAI 工具时的可用性和用户体验相关的评估量表，以及这些评估量表专门针对 CAI 必应聊天工具（即 Microsoft Copilot）的评估结果。以下量表是通过方便抽样（N = 126）的高等教育学生开发和评估的：感知有用性、一般可用性、可学习性、系统可靠性、视觉设计和导航、信息质量、信息显示、认知参与、设计吸引力、信任、人格化、风险感知和使用意向。上述大多数量表的内部一致性（Cronbach alpha）都在令人满意到良好的范围内，这意味着它们对进一步研究 CAI 工具的相关属性具有潜在的实用性。逐步线性回归显示，对未来使用必应聊天（或 ChatGPT）意向最有影响的预测因素是可用性变量 "感知有用性 "和两个用户体验变量--"信任 "和 "设计吸引力"。此外，我们的研究还显示，学生对必应聊天的各种具体可用性和用户体验特征的看法主要是积极的。所评估的评估量表将有助于进一步研究其他 CAI 工具，如 ChatGPT/GPT-4 和 Bard。
{"title":"Development of an Assessment Scale for Measurement of Usability and User Experience Characteristics of Bing Chat Conversational AI","authors":"G. Bubaš, Antonela Čižmešija, Andreja Kovačić","doi":"10.3390/fi16010004","DOIUrl":"https://doi.org/10.3390/fi16010004","url":null,"abstract":"After the introduction of the ChatGPT conversational artificial intelligence (CAI) tool in November 2022, there has been a rapidly growing interest in the use of such tools in higher education. While the educational uses of some other information technology (IT) tools (including collaboration and communication tools, learning management systems, chatbots, and videoconferencing tools) have been frequently evaluated regarding technology acceptance and usability attributes of those technologies, similar evaluations of CAI tools and services like ChatGPT, Bing Chat, and Bard have only recently started to appear in the scholarly literature. In our study, we present a newly developed set of assessment scales that are related to the usability and user experiences of CAI tools when used by university students, as well as the results of evaluation of these assessment scales specifically regarding the CAI Bing Chat tool (i.e., Microsoft Copilot). The following scales were developed and evaluated using a convenience sample (N = 126) of higher education students: Perceived Usefulness, General Usability, Learnability, System Reliability, Visual Design and Navigation, Information Quality, Information Display, Cognitive Involvement, Design Appeal, Trust, Personification, Risk Perception, and Intention to Use. For most of the aforementioned scales, internal consistency (Cronbach alpha) was in the range from satisfactory to good, which implies their potential usefulness for further studies of related attributes of CAI tools. A stepwise linear regression revealed that the most influential predictors of Intention to Use Bing Chat (or ChatGPT) in the future were the usability variable Perceived Usefulness and two user experience variables—Trust and Design Appeal. Also, our study revealed that students’ perceptions of various specific usability and user experience characteristics of Bing Chat were predominantly positive. The evaluated assessment scales could be beneficial in further research that would include other CAI tools like ChatGPT/GPT-4 and Bard.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"21 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139162767","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In recent years, the emergence of the smart city concept has garnered attention as a promising innovation aimed at addressing the multifactorial challenges arising from the concurrent trends of urban population growth and the climate crisis. In this study, we delve into the multifaceted dimensions of the smart city paradigm to unveil its underlying structure, employing a combination of quantitative and qualitative techniques. To achieve this, we collected textual data from three sources: scientific publication abstracts, news blog posts, and social media entries. For the analysis of this textual data, we introduce an innovative semi-automated methodology that integrates topic modeling and thematic analysis. Our findings highlight the intricate nature of the smart city domain, which necessitates examination from three perspectives: applications, technology, and socio-economic perspective. Through our analysis, we identified ten distinct aspects of the smart city paradigm, encompassing mobility, energy, infrastructure, environment, IoT, data, business, planning and administration, security, and people. When comparing the outcomes across the three diverse datasets, we noted a relative lack of attention within the scientific community towards certain aspects, notably in the realm of business, as well as themes relevant to citizens’ everyday lives, such as food, shopping, and green spaces. This work reveals the underlying thematic structure of the smart city concept to help researchers, practitioners, and public administrators participate effectively in smart city transformation initiatives. Furthermore, it introduces a novel data-driven method for conducting thematic analysis on large text datasets.
{"title":"Investigating the Key Aspects of a Smart City through Topic Modeling and Thematic Analysis","authors":"Anestis Kousis, Christos Tjortjis","doi":"10.3390/fi16010003","DOIUrl":"https://doi.org/10.3390/fi16010003","url":null,"abstract":"In recent years, the emergence of the smart city concept has garnered attention as a promising innovation aimed at addressing the multifactorial challenges arising from the concurrent trends of urban population growth and the climate crisis. In this study, we delve into the multifaceted dimensions of the smart city paradigm to unveil its underlying structure, employing a combination of quantitative and qualitative techniques. To achieve this, we collected textual data from three sources: scientific publication abstracts, news blog posts, and social media entries. For the analysis of this textual data, we introduce an innovative semi-automated methodology that integrates topic modeling and thematic analysis. Our findings highlight the intricate nature of the smart city domain, which necessitates examination from three perspectives: applications, technology, and socio-economic perspective. Through our analysis, we identified ten distinct aspects of the smart city paradigm, encompassing mobility, energy, infrastructure, environment, IoT, data, business, planning and administration, security, and people. When comparing the outcomes across the three diverse datasets, we noted a relative lack of attention within the scientific community towards certain aspects, notably in the realm of business, as well as themes relevant to citizens’ everyday lives, such as food, shopping, and green spaces. This work reveals the underlying thematic structure of the smart city concept to help researchers, practitioners, and public administrators participate effectively in smart city transformation initiatives. Furthermore, it introduces a novel data-driven method for conducting thematic analysis on large text datasets.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"28 4","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139164518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yashar Kor, Liang Tan, Petr Musilek, Marek Z. Reformat
Distribution grids are complex networks containing multiple pieces of equipment. These components are interconnected, and each of them is described by various attributes. A knowledge graph is an interesting data format that represents pieces of information as nodes and relations between the pieces as edges. In this paper, we describe the proposed vocabulary used to build a distribution system knowledge graph. We identify the concepts used in such graphs and a set of relations to represent links between concepts. Both provide a semantically rich representation of a system. Additionally, we offer a few illustrative examples of how a distributed system knowledge graph can be utilized to gain more insight into the operations of the grid. We show a simplified analysis of how outages can influence customers based on their locations and how adding DERs can influence/change it. These demonstrative use cases show that the graph-based representation of a distribution grid allows for integrating information of different types and how such a repository can be efficiently utilized. Based on the experiments with distribution system knowledge graphs presented in this article, we postulate that graph-based representation enables a novel way of storing information about power grids and facilitates interactive methods for their visualization and analysis.
配电网是包含多种设备的复杂网络。这些组件相互连接，每个组件都有不同的属性。知识图谱是一种有趣的数据格式，它将信息片段表示为节点，将片段之间的关系表示为边。本文介绍了用于构建配电系统知识图谱的拟议词汇。我们确定了此类图中使用的概念和一组表示概念间联系的关系。两者都为系统提供了丰富的语义表征。此外，我们还提供了一些示例，说明如何利用分布式系统知识图谱来深入了解网格的运行情况。我们简化分析了停电如何根据客户的位置影响客户，以及添加 DER 如何影响/改变停电。这些示范性用例表明，基于图形的配电网表示法可以整合不同类型的信息，以及如何有效利用这种信息库。基于本文介绍的配电系统知识图谱实验，我们推测基于图谱的表示法能够以一种新颖的方式存储电网信息，并促进可视化和分析的交互式方法。
{"title":"Integrating Knowledge Graphs into Distribution Grid Decision Support Systems","authors":"Yashar Kor, Liang Tan, Petr Musilek, Marek Z. Reformat","doi":"10.3390/fi16010002","DOIUrl":"https://doi.org/10.3390/fi16010002","url":null,"abstract":"Distribution grids are complex networks containing multiple pieces of equipment. These components are interconnected, and each of them is described by various attributes. A knowledge graph is an interesting data format that represents pieces of information as nodes and relations between the pieces as edges. In this paper, we describe the proposed vocabulary used to build a distribution system knowledge graph. We identify the concepts used in such graphs and a set of relations to represent links between concepts. Both provide a semantically rich representation of a system. Additionally, we offer a few illustrative examples of how a distributed system knowledge graph can be utilized to gain more insight into the operations of the grid. We show a simplified analysis of how outages can influence customers based on their locations and how adding DERs can influence/change it. These demonstrative use cases show that the graph-based representation of a distribution grid allows for integrating information of different types and how such a repository can be efficiently utilized. Based on the experiments with distribution system knowledge graphs presented in this article, we postulate that graph-based representation enables a novel way of storing information about power grids and facilitates interactive methods for their visualization and analysis.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"55 3","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139168869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The paper presents an experimental security assessment within two widely used open-source 5G projects, namely Open5GS and OAI (Open-Air Interface). The examination concentrates on two network functions (NFs) that are externally exposed within the core network architecture, i.e., the Access and Mobility Management Function (AMF) and the Network Repository Function/Network Exposure Function (NRF/NEF) of the Service-Based Architecture (SBA). Focusing on the Service-Based Interface (SBI) of these exposed NFs, the analysis not only identifies potential security gaps but also underscores the crucial role of Mobile Network Operators (MNOs) in implementing robust security measures. Furthermore, given the shift towards Network Function Virtualization (NFV), this paper emphasizes the importance of secure development practices to enhance the integrity of 5G network functions. In essence, this paper underscores the significance of scrutinizing security vulnerabilities in open-source 5G projects, particularly within the core network’s SBI and externally exposed NFs. The research outcomes provide valuable insights for MNOs, enabling them to establish effective security measures and promote secure development practices to safeguard the integrity of 5G network functions. Additionally, the empirical investigation aids in identifying potential vulnerabilities in open-source 5G projects, paving the way for future enhancements and standard releases.
{"title":"A Vulnerability Assessment of Open-Source Implementations of Fifth-Generation Core Network Functions","authors":"Filippo Dolente, R. Garroppo, Michele Pagano","doi":"10.3390/fi16010001","DOIUrl":"https://doi.org/10.3390/fi16010001","url":null,"abstract":"The paper presents an experimental security assessment within two widely used open-source 5G projects, namely Open5GS and OAI (Open-Air Interface). The examination concentrates on two network functions (NFs) that are externally exposed within the core network architecture, i.e., the Access and Mobility Management Function (AMF) and the Network Repository Function/Network Exposure Function (NRF/NEF) of the Service-Based Architecture (SBA). Focusing on the Service-Based Interface (SBI) of these exposed NFs, the analysis not only identifies potential security gaps but also underscores the crucial role of Mobile Network Operators (MNOs) in implementing robust security measures. Furthermore, given the shift towards Network Function Virtualization (NFV), this paper emphasizes the importance of secure development practices to enhance the integrity of 5G network functions. In essence, this paper underscores the significance of scrutinizing security vulnerabilities in open-source 5G projects, particularly within the core network’s SBI and externally exposed NFs. The research outcomes provide valuable insights for MNOs, enabling them to establish effective security measures and promote secure development practices to safeguard the integrity of 5G network functions. Additionally, the empirical investigation aids in identifying potential vulnerabilities in open-source 5G projects, paving the way for future enhancements and standard releases.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":" 34","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138961327","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Duy Tung Khanh Nguyen, D. Duong, Willy Susilo, Yang-Wai Chow, The Anh Ta
Homomorphic encryption (HE) has emerged as a pivotal technology for secure neural network inference (SNNI), offering privacy-preserving computations on encrypted data. Despite active developments in this field, HE-based SNNI frameworks are impeded by three inherent limitations. Firstly, they cannot evaluate non-linear functions such as ReLU, the most widely adopted activation function in neural networks. Secondly, the permitted number of homomorphic operations on ciphertexts is bounded, consequently limiting the depth of neural networks that can be evaluated. Thirdly, the computational overhead associated with HE is prohibitively high, particularly for deep neural networks. In this paper, we introduce a novel paradigm designed to address the three limitations of HE-based SNNI. Our approach is an interactive approach that is solely based on HE, called iLHE. Utilizing the idea of iLHE, we present two protocols: ReLU, which facilitates the direct evaluation of the ReLU function on encrypted data, tackling the first limitation, and HeRefresh, which extends the feasible depth of neural network computations and mitigates the computational overhead, thereby addressing the second and third limitations. Based on HeReLU and HeRefresh protocols, we build a new framework for SNNI, named HeFUN. We prove that our protocols and the HeFUN framework are secure in the semi-honest security model. Empirical evaluations demonstrate that HeFUN surpasses current HE-based SNNI frameworks in multiple aspects, including security, accuracy, the number of communication rounds, and inference latency. Specifically, for a convolutional neural network with four layers on the MNIST dataset, HeFUN achieves 99.16% accuracy with an inference latency of 1.501 s, surpassing the popular HE-based framework CryptoNets proposed by Gilad-Bachrach, which achieves 98.52% accuracy with an inference latency of 3.479 s.
同态加密（HE）已成为安全神经网络推理（SNNI）的一项关键技术，可对加密数据进行隐私保护计算。尽管该领域发展活跃，但基于 HE 的 SNNI 框架仍受到三个固有限制的阻碍。首先，它们无法评估非线性函数，如神经网络中最广泛采用的激活函数 ReLU。其次，允许对密码文本进行的同态操作的数量是有限制的，因此限制了可评估的神经网络的深度。第三，与 HE 相关的计算开销过高，尤其是对深度神经网络而言。在本文中，我们介绍了一种新型范式，旨在解决基于 HE 的 SNNI 的三个局限性。我们的方法是一种完全基于 HE 的交互式方法，称为 iLHE。利用 iLHE 的理念，我们提出了两个协议：ReLU（便于在加密数据上直接评估 ReLU 函数）和 HeRefresh（扩展神经网络计算的可行深度并减少计算开销）协议解决了第一个限制，从而解决了第二个和第三个限制。在 HeReLU 和 HeRefresh 协议的基础上，我们为 SNNI 构建了一个新框架，命名为 HeFUN。我们证明了我们的协议和 HeFUN 框架在半诚信安全模型中是安全的。经验评估表明，HeFUN 在安全性、准确性、通信轮数和推理延迟等多个方面都超越了目前基于 HE 的 SNNI 框架。具体来说，对于 MNIST 数据集上的四层卷积神经网络，HeFUN 的准确率达到了 99.16%，推理延迟为 1.501 秒，超过了 Gilad-Bachrach 提出的基于 HE 的流行框架 CryptoNets，后者的准确率为 98.52%，推理延迟为 3.479 秒。
{"title":"HeFUN: Homomorphic Encryption for Unconstrained Secure Neural Network Inference","authors":"Duy Tung Khanh Nguyen, D. Duong, Willy Susilo, Yang-Wai Chow, The Anh Ta","doi":"10.3390/fi15120407","DOIUrl":"https://doi.org/10.3390/fi15120407","url":null,"abstract":"Homomorphic encryption (HE) has emerged as a pivotal technology for secure neural network inference (SNNI), offering privacy-preserving computations on encrypted data. Despite active developments in this field, HE-based SNNI frameworks are impeded by three inherent limitations. Firstly, they cannot evaluate non-linear functions such as ReLU, the most widely adopted activation function in neural networks. Secondly, the permitted number of homomorphic operations on ciphertexts is bounded, consequently limiting the depth of neural networks that can be evaluated. Thirdly, the computational overhead associated with HE is prohibitively high, particularly for deep neural networks. In this paper, we introduce a novel paradigm designed to address the three limitations of HE-based SNNI. Our approach is an interactive approach that is solely based on HE, called iLHE. Utilizing the idea of iLHE, we present two protocols: ReLU, which facilitates the direct evaluation of the ReLU function on encrypted data, tackling the first limitation, and HeRefresh, which extends the feasible depth of neural network computations and mitigates the computational overhead, thereby addressing the second and third limitations. Based on HeReLU and HeRefresh protocols, we build a new framework for SNNI, named HeFUN. We prove that our protocols and the HeFUN framework are secure in the semi-honest security model. Empirical evaluations demonstrate that HeFUN surpasses current HE-based SNNI frameworks in multiple aspects, including security, accuracy, the number of communication rounds, and inference latency. Specifically, for a convolutional neural network with four layers on the MNIST dataset, HeFUN achieves 99.16% accuracy with an inference latency of 1.501 s, surpassing the popular HE-based framework CryptoNets proposed by Gilad-Bachrach, which achieves 98.52% accuracy with an inference latency of 3.479 s.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"38 1","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138995228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The e-book services we use today have a serious drawback in that we will no longer be able to read the books we have purchased when the service is terminated. One way to solve this problem is to build a decentralized system that does not depend on a specific company or organization by combining smart contracts running on the Ethereum blockchain and distributed storage such as an IPFS. However, a simple combination of existing technologies does not make the stored e-book data persistent, so the risk of purchased e-books becoming unreadable remains. In this paper, we propose a decentralized distributed storage called d-book-repository, which has both access management function and data durability for purchased e-books. This system uses NFTs as access rights to realize strict access control by preventing clients who do not have NFTs from downloading e-book data. In addition, e-book data stored on storage nodes in the distributed storage is divided into shards using Reed–Solomon codes, and each storage node stores only a single shard, thereby preventing the creation of nodes that can restore the entire content from locally stored data. The storage of each shard is not handled by a single node but by a group of nodes, and the shard is propagated to all nodes in the group using the gossip protocol, where erasure codes are utilized to increase the resilience against node departure. Furthermore, an incentive mechanism to encourage participation as a storage node is implemented using smart contracts. We built a prototype of the proposed system on AWS and evaluated its performance. The results showed that both downloading and uploading 100 MB of e-book data (equivalent to one comic book) were completed within 10 s using an instance type of m5.xlarge. This value is only 1.3 s longer for downloading and 2.2 s longer for uploading than the time required for a simple download/upload without access control, confirming that the overhead associated with the proposed method is sufficiently small.
{"title":"Decentralized Storage with Access Control and Data Persistence for e-Book Stores","authors":"Keigo Ogata, Satoshi Fujita","doi":"10.3390/fi15120406","DOIUrl":"https://doi.org/10.3390/fi15120406","url":null,"abstract":"The e-book services we use today have a serious drawback in that we will no longer be able to read the books we have purchased when the service is terminated. One way to solve this problem is to build a decentralized system that does not depend on a specific company or organization by combining smart contracts running on the Ethereum blockchain and distributed storage such as an IPFS. However, a simple combination of existing technologies does not make the stored e-book data persistent, so the risk of purchased e-books becoming unreadable remains. In this paper, we propose a decentralized distributed storage called d-book-repository, which has both access management function and data durability for purchased e-books. This system uses NFTs as access rights to realize strict access control by preventing clients who do not have NFTs from downloading e-book data. In addition, e-book data stored on storage nodes in the distributed storage is divided into shards using Reed–Solomon codes, and each storage node stores only a single shard, thereby preventing the creation of nodes that can restore the entire content from locally stored data. The storage of each shard is not handled by a single node but by a group of nodes, and the shard is propagated to all nodes in the group using the gossip protocol, where erasure codes are utilized to increase the resilience against node departure. Furthermore, an incentive mechanism to encourage participation as a storage node is implemented using smart contracts. We built a prototype of the proposed system on AWS and evaluated its performance. The results showed that both downloading and uploading 100 MB of e-book data (equivalent to one comic book) were completed within 10 s using an instance type of m5.xlarge. This value is only 1.3 s longer for downloading and 2.2 s longer for uploading than the time required for a simple download/upload without access control, confirming that the overhead associated with the proposed method is sufficiently small.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":" 7","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138964453","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
J. M. Adeke, Guangjie Liu, Junjie Zhao, Nannan Wu, Hafsat Muhammad Bashir
Machine learning (ML) models are essential to securing communication networks. However, these models are vulnerable to adversarial examples (AEs), in which malicious inputs are modified by adversaries to produce the desired output. Adversarial training is an effective defense method against such attacks but relies on access to a substantial number of AEs, a prerequisite that entails significant computational resources and the inherent limitation of poor performance on clean data. To address these problems, this study proposes a novel approach to improve the robustness of ML-based network traffic classification models by integrating derived variables (DVars) into training. Unlike adversarial training, our approach focuses on enhancing training using DVars, introducing randomness into the input data. DVars are generated from the baseline dataset and significantly improve the resilience of the model to AEs. To evaluate the effectiveness of DVars, experiments were conducted using the CSE-CIC-IDS2018 dataset and three state-of-the-art ML-based models: decision tree (DT), random forest (RF), and k-neighbors (KNN). The results show that DVars can improve the accuracy of KNN under attack from 0.45% to 0.84% for low-intensity attacks and from 0.32% to 0.66% for high-intensity attacks. Furthermore, both DT and RF achieve a significant increase in accuracy when subjected to attack of different intensity. Moreover, DVars are computationally efficient, scalable, and do not require access to AEs.
机器学习（ML）模型对于确保通信网络安全至关重要。然而，这些模型很容易受到对抗范例（AE）的攻击，在对抗范例中，恶意输入会被对抗者修改以产生所需的输出。对抗训练是抵御此类攻击的有效方法，但它依赖于对大量 AE 的访问，而访问 AE 的前提条件是需要大量的计算资源，其固有的限制是在干净数据上的性能较差。为了解决这些问题，本研究提出了一种新方法，通过将衍生变量（DVars）整合到训练中来提高基于 ML 的网络流量分类模型的鲁棒性。与对抗训练不同，我们的方法侧重于使用 DVars 增强训练，将随机性引入输入数据。DVars 由基线数据集生成，可显著提高模型对 AE 的适应能力。为了评估 DVars 的有效性，我们使用 CSE-CIC-IDS2018 数据集和三种最先进的基于 ML 的模型进行了实验：决策树（DT）、随机森林（RF）和 KNN（Kneighbors）。结果表明，在低强度攻击下，DVars 可以将 KNN 的准确率从 0.45% 提高到 0.84%；在高强度攻击下，DVars 可以将 KNN 的准确率从 0.32% 提高到 0.66%。此外，当受到不同强度的攻击时，DT 和 RF 都能显著提高准确率。此外，DVars 的计算效率高、可扩展，而且不需要访问 AE。
{"title":"Securing Network Traffic Classification Models against Adversarial Examples Using Derived Variables","authors":"J. M. Adeke, Guangjie Liu, Junjie Zhao, Nannan Wu, Hafsat Muhammad Bashir","doi":"10.3390/fi15120405","DOIUrl":"https://doi.org/10.3390/fi15120405","url":null,"abstract":"Machine learning (ML) models are essential to securing communication networks. However, these models are vulnerable to adversarial examples (AEs), in which malicious inputs are modified by adversaries to produce the desired output. Adversarial training is an effective defense method against such attacks but relies on access to a substantial number of AEs, a prerequisite that entails significant computational resources and the inherent limitation of poor performance on clean data. To address these problems, this study proposes a novel approach to improve the robustness of ML-based network traffic classification models by integrating derived variables (DVars) into training. Unlike adversarial training, our approach focuses on enhancing training using DVars, introducing randomness into the input data. DVars are generated from the baseline dataset and significantly improve the resilience of the model to AEs. To evaluate the effectiveness of DVars, experiments were conducted using the CSE-CIC-IDS2018 dataset and three state-of-the-art ML-based models: decision tree (DT), random forest (RF), and k-neighbors (KNN). The results show that DVars can improve the accuracy of KNN under attack from 0.45% to 0.84% for low-intensity attacks and from 0.32% to 0.66% for high-intensity attacks. Furthermore, both DT and RF achieve a significant increase in accuracy when subjected to attack of different intensity. Moreover, DVars are computationally efficient, scalable, and do not require access to AEs.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"21 3","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138967719","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Despite its status as one of the most ancient sectors worldwide, agriculture continues to be a fundamental cornerstone of the global economy. Nevertheless, it faces obstacles such as a lack of trust, difficulties in tracking, and inefficiencies in managing the supply chain. This article examines the potential of blockchain technology (BCT) to alter the agricultural industry by providing a decentralized, transparent, and unchangeable solution to meet the difficulties it faces. The initial discussion provides an overview of the challenges encountered by the agricultural industry, followed by a thorough analysis of BCT, highlighting its potential advantages. Following that, the article explores other agricultural uses for blockchain technology, such as managing supply chains, verifying products, and processing payments. In addition, this paper examines the constraints and challenges related to the use of blockchain technology in agriculture, including issues such as scalability, legal frameworks, and interoperability. This paper highlights the potential of BCT to transform the agricultural industry by offering a transparent and secure platform for managing the supply chain. Nevertheless, it emphasizes the need for involving stakeholders, having clear legislation, and possessing technical skills in order to achieve effective implementation. This work utilizes a systematic literature review using the PRISMA technique and applies meta-analysis as the research methodology, enabling a thorough investigation of the present information available. The results emphasize the significant and positive effect of BCT on agriculture, emphasizing the need for cooperative endeavors among governments, industry pioneers, and technology specialists to encourage its extensive implementation and contribute to the advancement of a sustainable and resilient food system.
{"title":"Blockchain in Agriculture to Ensure Trust, Effectiveness, and Traceability from Farm Fields to Groceries","authors":"Arvind Panwar, Manju Khari, Sanjay Misra, Urvashi Sugandh","doi":"10.3390/fi15120404","DOIUrl":"https://doi.org/10.3390/fi15120404","url":null,"abstract":"Despite its status as one of the most ancient sectors worldwide, agriculture continues to be a fundamental cornerstone of the global economy. Nevertheless, it faces obstacles such as a lack of trust, difficulties in tracking, and inefficiencies in managing the supply chain. This article examines the potential of blockchain technology (BCT) to alter the agricultural industry by providing a decentralized, transparent, and unchangeable solution to meet the difficulties it faces. The initial discussion provides an overview of the challenges encountered by the agricultural industry, followed by a thorough analysis of BCT, highlighting its potential advantages. Following that, the article explores other agricultural uses for blockchain technology, such as managing supply chains, verifying products, and processing payments. In addition, this paper examines the constraints and challenges related to the use of blockchain technology in agriculture, including issues such as scalability, legal frameworks, and interoperability. This paper highlights the potential of BCT to transform the agricultural industry by offering a transparent and secure platform for managing the supply chain. Nevertheless, it emphasizes the need for involving stakeholders, having clear legislation, and possessing technical skills in order to achieve effective implementation. This work utilizes a systematic literature review using the PRISMA technique and applies meta-analysis as the research methodology, enabling a thorough investigation of the present information available. The results emphasize the significant and positive effect of BCT on agriculture, emphasizing the need for cooperative endeavors among governments, industry pioneers, and technology specialists to encourage its extensive implementation and contribute to the advancement of a sustainable and resilient food system.","PeriodicalId":37982,"journal":{"name":"Future Internet","volume":"47 10","pages":""},"PeriodicalIF":3.4,"publicationDate":"2023-12-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"138967378","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：