共查询到20条相似文献，搜索用时 31 毫秒
1.
《Information processing & management》2023,60(1):103167
Federated Learning (FL) is a platform for smart healthcare systems that use wearables and other Internet of Things enabled devices. However, source inference attacks (SIAs) can infer the connection between physiological data in training datasets with FL clients and reveal the identities of participants to the attackers. We propose a comprehensive smart healthcare framework for sharing physiological data, named FRESH, that is based on FL and ring signature defense from the attacks. In FRESH, physiological data are collected from individuals by wearable devices. These data are processed by edge computing devices (e.g., mobile phones, tablet PCs) that train ML models using local data. The model parameters are uploaded by edge computing devices to the central server for joint training of FL models of disease prediction. In this procedure, certificateless ring signature is used to hide the source of parameter updates during joint training for FL to effectively resist SIAs. In the proposed ring signature schema, an improved batch verification algorithm is designed to leverage additivity of linear operations on elliptic curves and to help reduce the computing workload of the server. Experimental results demonstrate that FRESH effectively reduces the success rate of SIAs and the batch verification method significantly improves the efficiency of signature verification. FRESH can be applied to large scale smart healthcare systems with FL involving large numbers of users. 相似文献
2.
《Journal of The Franklin Institute》2023,360(12):8669-8703
In the traditional distributed machine learning scenario, the user’s private data is transmitted between clients and a central server, which results in significant potential privacy risks. In order to balance the issues of data privacy and joint training of models, federated learning (FL) is proposed as a particular distributed machine learning procedure with privacy protection mechanisms, which can achieve multi-party collaborative computing without revealing the original data. However, in practice, FL faces a variety of challenging communication problems. This review seeks to elucidate the relationship between these communication issues by methodically assessing the development of FL communication research from three perspectives: communication efficiency, communication environment, and communication resource allocation. Firstly, we sort out the current challenges existing in the communications of FL. Second, we have collated FL communications-related papers and described the overall development trend of the field based on their logical relationship. Ultimately, we discuss the future directions of research for communications in FL. 相似文献
3.
《Information processing & management》2023,60(3):103211
As the number of clients for federated learning (FL) has expanded to the billion level, a new research branch named secure federated submodel learning (SFSL) has emerged. In SFSL, mobile clients only download a tiny ratio of the global model from the coordinator’s global. However, SFSL provides little guarantees on the convergence and accuracy performance as the covered items may be highly biased. In this work, we formulate the problem of client selection through optimizing unbiased coverage of item index set for enhancing SFSL performance. We analyze the NP-hardness of this problem and propose a novel heuristic multi-group client selection framework by jointly optimizing index diversity and similarity. Specifically, heuristic exploration on some random client groups are performed progressively for an empirical approximate solution. Meanwhile, private set operations are used to preserve the privacy of participated clients. We implement the proposal by simulating large-scale SFSL application in a lab environment and conduct evaluations on two real-world data-sets. The results demonstrate the performance (w.r.t., accuracy and convergence speed) superiority of our selection algorithm than SFSL. The proposal is also shown to yield significant computation advantage with similar communication performance as SFSL. 相似文献
4.
《Information processing & management》2023,60(2):103212
The massive number of Internet of Things (IoT) devices connected to the Internet is continuously increasing. The operations of these devices rely on consuming huge amounts of energy. Power limitation is a major issue hindering the operation of IoT applications and services. To improve operational visibility, Low-power devices which constitute IoT networks, drive the need for sustainable sources of energy to carry out their tasks for a prolonged period of time. Moreover, the means to ensure energy sustainability and QoS must consider the stochastic nature of the energy supplies and dynamic IoT environments. Artificial Intelligence (AI) enhanced protocols and algorithms are capable of predicting and forecasting demand as well as providing leverage at different stages of energy use to supply. AI will improve the efficiency of energy infrastructure and decrease waste in distributed energy systems, ensuring their long-term viability. In this paper, we conduct a survey to explore enhanced AI-based solutions to achieve energy sustainability in IoT applications. AI is relevant through the integration of various Machine Learning (ML) and Swarm Intelligence (SI) techniques in the design of existing protocols. ML mechanisms used in the literature include variously supervised and unsupervised learning methods as well as reinforcement learning (RL) solutions. The survey constitutes a complete guideline for readers who wish to get acquainted with recent development and research advances in AI-based energy sustainability in IoT Networks. The survey also explores the different open issues and challenges. 相似文献
5.
Jiun-Hung Ding Roger Chien Shih-Hao Hung Yi-Lan Lin Che-Yang Kuo Ching-Hsien Hsu Yeh-Ching Chung 《International Journal of Information Management》2014
As mobile networks and devices being rapidly innovated, many new Internet services and applications have been deployed. However, the current implementation faces security, management, and performance issues, which are critical to the use in business environments. Migrating sensitive information, management facilities, and intensive computation to security hardened virtualized environment in the cloud provides effective solutions. This paper proposes an innovative Internet service and business model to provide a secure and consolidated environment for enterprise mobile information management based on the infrastructure of cloud-based virtual phones (CVP). Our proposed solution enables the users to execute Android and web applications in the cloud and connect to other users of CVP with enhanced performance and protected privacy. The organization of CVP can be mixed with centralized control and distributed protocols, which emulates the behavior of human societies. This minimizes the need to handle sensitive data in mobile devices, eases the management of data, and reduces the overhead of mobile application deployment. 相似文献
6.
《Information processing & management》2023,60(2):103162
Federated learning (FL), as a popular distributed machine learning paradigm, has driven the integration of knowledge in ubiquitous data owners under one roof. Although designed for privacy-preservation by nature, the supposed well-sanitized parameters still convey sensitive information (e.g., reconstruction attack), while existing technical countermeasures provide weak explainability for privacy understanding and protection practices of general users. This work investigates these privacy concerns with an exploratory study and elaborates on data owners’ expectations in FL. Based on the analysis, we design the first interactive visualization system for FL privacy that supports intelligible privacy inspection and adjustment for data owners. Specifically, our proposal facilitates sample recommendation for joint privacy–performance training at cold start. Then it provides visual interpretation and attention rendering of privacy risks in view of multiple attacking channels and a holistic view. Further it supports interactive privacy enhancement involving both user initiative and differential privacy technique, and iterative trade-off with real-time inference accuracy estimation. We evaluate the effectiveness of the system and collect qualitative feedbacks from users. The results demonstrate that 96.7% of users acknowledge the benefits to privacy inspection and adjustment and 90.3% are willing to use our system. More importantly, 87.1% increase the willingness of contributing data for FL. 相似文献
7.
《Information processing & management》2022,59(6):103061
Federated Learning (FL) has been foundational in improving the performance of a wide range of applications since it was first introduced by Google. Some of the most prominent and commonly used FL-powered applications are Android’s Gboard for predictive text and Google Assistant. FL can be defined as a setting that makes on-device, collaborative Machine Learning possible. A wide range of literature has studied FL technical considerations, frameworks, and limitations with several works presenting a survey of the prominent literature on FL. However, prior surveys have focused on technical considerations and challenges of FL, and there has been a limitation in more recent work that presents a comprehensive overview of the status and future trends of FL in applications and markets. In this survey, we introduce the basic fundamentals of FL, describing its underlying technologies, architectures, system challenges, and privacy-preserving methods. More importantly, the contribution of this work is in scoping a wide variety of FL current applications and future trends in technology and markets today. We present a classification and clustering of literature progress in FL in application to technologies including Artificial Intelligence, Internet of Things, blockchain, Natural Language Processing, autonomous vehicles, and resource allocation, as well as in application to market use cases in domains of Data Science, healthcare, education, and industry. We discuss future open directions and challenges in FL within recommendation engines, autonomous vehicles, IoT, battery management, privacy, fairness, personalization, and the role of FL for governments and public sectors. By presenting a comprehensive review of the status and prospects of FL, this work serves as a reference point for researchers and practitioners to explore FL applications under a wide range of domains. 相似文献
8.
9.
伴随全球范围的无线技术和移动通信技术的快速发展,移动学习（MobileLearning）代表着一种新的学习趋势在教育领域应运而生,并逐渐成为自主学习和终身学习的发展趋势和研究热点。就3G通信技术下移动学习系统的构建、关键技术及存在的问题进行了相关阐述和探讨,期望为国内移动学习业务的开拓者提供借鉴与参考。 相似文献
10.
11.
12.
With the deployment of fifth-generation (5G) wireless networks worldwide, research on sixth-generation (6G) wireless communications has commenced. It is expected that 6G networks can accommodate numerous heterogeneous devices and infrastructures with enhanced efficiency and security over diverse, e.g. spectrum, computing and storage, resources. However, this goal is impeded by a number of trust-related issues that are often neglected in network designs. Blockchain, as an innovative and revolutionary technology that has arisen in the recent decade, provides a promising solution. Building on its nature of decentralization, transparency, anonymity, immutability, traceability and resiliency, blockchain can establish cooperative trust among separate network entities and facilitate, e.g. efficient resource sharing, trusted data interaction, secure access control, privacy protection, and tracing, certification and supervision functionalities for wireless networks, thus presenting a new paradigm towards 6G. This paper is dedicated to blockchain-enabled wireless communication technologies. We first provide a brief introduction to the fundamentals of blockchain, and then we conduct a comprehensive investigation of the most recent efforts in incorporating blockchain into wireless communications from several aspects. Importantly, we further propose a unified framework of the blockchain radio access network (B-RAN) as a trustworthy and secure paradigm for 6G networking by utilizing blockchain technologies with enhanced efficiency and security. The critical elements of B-RAN, such as consensus mechanisms, smart contract, trustworthy access, mathematical modeling, cross-network sharing, data tracking and auditing and intelligent networking, are elaborated. We also provide the prototype design of B-RAN along with the latest experimental results. 相似文献
13.
Sajjad Rahmani Dabbagh Fazle Rabbi Zafer Doan Ali Kemal Yetisen Savas Tasoglu 《Biomicrofluidics》2020,14(6)
High-throughput, cost-effective, and portable devices can enhance the performance of point-of-care tests. Such devices are able to acquire images from samples at a high rate in combination with microfluidic chips in point-of-care applications. However, interpreting and analyzing the large amount of acquired data is not only a labor-intensive and time-consuming process, but also prone to the bias of the user and low accuracy. Integrating machine learning (ML) with the image acquisition capability of smartphones as well as increasing computing power could address the need for high-throughput, accurate, and automatized detection, data processing, and quantification of results. Here, ML-supported diagnostic technologies are presented. These technologies include quantification of colorimetric tests, classification of biological samples (cells and sperms), soft sensors, assay type detection, and recognition of the fluid properties. Challenges regarding the implementation of ML methods, including the required number of data points, image acquisition prerequisites, and execution of data-limited experiments are also discussed. 相似文献
14.
Users increasingly use mobile devices to engage in social activity and commerce, enabling new forms of data collection by firms and marketers. User privacy expectations for these new forms of data collection remain unclear. A particularly difficult challenge is meeting expectations for contextual integrity, as user privacy expectations vary depending upon data type collected and context of use. This article illustrates how fine-grained, contextual privacy expectations can be measured. It presents findings from a factorial vignette survey that measured the impact of diverse real-world contexts (e.g., medical, navigation, music), data types, and data uses on user privacy expectations. Results demonstrate that individuals’ general privacy preferences are of limited significance for predicting their privacy judgments in specific scenarios. Instead, the results present a nuanced portrait of the relative importance of particular contextual factors and information uses, and demonstrate how those contextual factors can be found and measured. The results also suggest that current common activities of mobile application companies, such as harvesting and reusing location data, images, and contact lists, do not meet users’ privacy expectations. Understanding how user privacy expectations vary according to context, data types, and data uses highlights areas requiring stricter privacy protections by governments and industry. 相似文献
15.
In this paper, we employ Extended Cognition as a background for a series of thought experiments about privacy and common used information technology devices. Laptops and smart phones are now widely used devices, but current privacy standards do not adequately address the relationship between the owners of these devices and the information stored on them. Law enforcement treats laptops and smart phones are potential sources of information about criminal activity, but this treatment ignores the use of smart devices as extensions of users’ cognitive capability. In Philosophy of Mind, Extended Cognition is a metaphysical theory about the relationship between consciousness or cognitive activity and various external tools or aids that agents employ in the service of cognition. Supporters of Extended Cognition argue that mental activity must be understood as taking place both within the brain and by way of tools such as a logician’s pen and paper, a mathematician’s calculator, or a writer’s word processing program. While Extended Cognition does not have universal support among philosophers of mind, the theory nevertheless describes how agents interact with their “smart devices.” We explore the the implications of taking Extended Cognition seriously with regard to privacy concerns by way of a series of thought experiments. By comparing the differences in expectations of privacy between a citizen and the government, between an employee of a corporate firm, and between citizens alone, we show that expectations of privacy and injury are significantly affected by taking the cognitive role of smart devices into account. 相似文献
16.
针对大数据环境下用户信息隐私泄露问题,论文首先分析当前用户信息隐私保护的现状与趋势,并指出当前用户信息隐私保护存在的问题;然后通过典型案例、统计分析和系统分析等手段,研究大数据环境下用户信息隐私泄露的发生机制和成因;最后聚焦用户信息隐私泄露的成因,分析研究用户信息隐私保护的关键社会方法与技术方法,并构建用户信息隐私保护的社会技术模型以及优化策略。 相似文献
17.
《Information processing & management》2022,59(5):103036
The development of Management Information Systems (MIS) is impossible without the use of machine learning (ML). It's a type of Artificial Intelligence (AI) that makes predictions using statistical models. When it comes to financial analysis, there are numerous risk-related concerns to contend with today (FI). In the financial sector, machine learning algorithms are used to detect fraud, automate trading, and provide financial advice to investors. To better serve its customers, the financial sector can now save borrower data according to specific criteria thanks to MIS. In fact, there is a large amount of data about debtors, making load management a difficult task. ML can examine millions of data sets in a short period of time without being explicitly programmed to improve the results. This type of algorithm can aid financial institutions in making grant selections for their clients. For the objective of classifying FI in terms of fraud or not, the Intelligent Information System for Financial Institutions (IISFI) relying on Supervised ML (SML) Algorithms has been created in this work. Bayesian Belief Network, Neural Network, Decision trees, Naïve Bayes, and Nearest Neighbor has been compared for the purpose of classifying FI risks using the performance measures asfalse positive rate, true positive rate, true negative rate, false negative rate, accuracy, F-Measure, Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Square Error (RMSE), Med AE, Receiver Operating Characteristic (ROC) area,Precision Recall Characteristic (PRC) area, and measures of PC. 相似文献
18.
《International Journal of Information Management》2016,36(5):724-734
Over the past decade, social media technologies have become effective tools not only for entertainment, but also for online health communications. In virtual health communities (VHCs), the members often share their personal health information (PHI) with other members. These information exchanges provide benefits to both the information providers as well as the recipients. The PHI disclosure, however, may entail privacy concerns. Our study used the privacy calculus model to examine the trade-off between individuals’ expected benefits and privacy concerns when disclosing PHI in social media environments. Our results showed that age, health status, and affective commitment influence the balance between the information disclosure drivers and barriers in the privacy calculus model. More specifically, we found that among members of VHCs, healthier people expect to receive fewer personal benefits of communicating PHI in social media environments. Moreover, individuals who are emotionally attached to online communities expect to both receive and provide more benefits while communicating PHI in those communities. We also observed that individuals who are familiar with but not members of VHCs, especially those who are young and healthy, are more concerned about their PHI privacy in online communities. 相似文献
19.
KDD, data mining, and the challenge for normative privacy 总被引：3，自引：1，他引：2
Herman T. Tavani 《Ethics and Information Technology》1999,1(4):265-273
The present study examines certain challenges that KDD (Knowledge Discovery in Databases) in general and data mining in particular pose for normative privacy and public policy. In an earlier work (see Tavani, 1999), I argued that certain applications of data-mining technology involving the manipulation of personal data raise special privacy concerns. Whereas the main purpose of the earlier essay was to show what those specific privacy concerns are and to describe how exactly those concerns have been introduced by the use of certain KDD and data-mining techniques, the present study questions whether the use of those techniques necessarily violates the privacy of individuals. This question is considered vis-à-vis a recent theory of privacy advanced by James Moor (1997). The implications of that privacy theory for a data-mining policy are also considered. 相似文献
20.
[目的/意义] 大数据环境下,APP已经成为工作、生活、娱乐甚至是赚钱的重要工具,与此同时,APP也成为用户隐私泄露的重灾区。用户一方面担心隐私的泄露,另外一方面由于APP所带来的益处,却愿意主动提供隐私数据供商家利用,这就是所谓的"隐私悖论"现象。[方法/过程] 隐私计算是研究隐私悖论的重要方法之一,通过对APP用户隐私计算影响因素的调查,分析影响用户自愿提供隐私数据的核心因素,并分析悖论存在的原因。[结果/结论] APP用户隐私的保护需要不断加强法律、制度的建设和开发商与运营商的监管,而不断提高用户隐私保护的意识也是不可忽视的重要内容。 相似文献