A classification-based privacy-preserving decision-making for secure data sharing in Internet of Things assisted applications

The introduction of the Internet of Things (IoT) paradigm serves as pervasive resource access and sharing platform for different real-time applications. Decentralized resource availability, access, and allocation provide a better quality of user experience regardless of the application type and scenario. However, privacy remains an open issue in this ubiquitous sharing platform due to massive and replicated data availability. In this paper, privacy-preserving decision-making for the data-sharing scheme is introduced. This scheme is responsible for improving the security in data sharing without the impact of replicated resources on communicating users. In this scheme, classification learning is used for identifying replicas and accessing granted resources independently. Based on the trust score of the available resources, this classification is recurrently performed to improve the reliability of information sharing. The user-level decisions for information sharing and access are made using the classification of the resources at the time of availability. This proposed scheme is verified using the metrics access delay, success ratio, computation complexity, and sharing loss.     

物联网中带有隐私保护的鲁棒联邦学习研究

联邦学习允许数据不出本地的情况下实现数据价值的有效流动,被认为是物联网(IoT)场景下兼顾数据共享与隐私保护的有效方法。然而,联邦学习系统易受拜占庭攻击和推理攻击的影响,导致系统的鲁棒性和数据的隐私性受损。物联网设备的数据异构性和资源瓶颈,也为带有隐私保护的鲁棒聚合算法设计带来巨大挑战。该文提出面向异构物联网的带有数据重采样的鲁棒聚合方法Re-Sim,通过测量方向相似性和标准化更新幅度实现模型的鲁棒聚合,并采用数据重采样技术增强数据异构环境下模型的鲁棒性。同时构建轻量安全聚合协议(LSA),在保证数据隐私性的同时兼顾模型鲁棒性、准确性和计算开销,并从理论上对协议的隐私性进行了分析。仿真结果表明,该方案能在数据异构情况下有效抵抗拜占庭攻击和推理攻击,与基线方法相比,该文所提方案精度提高1%～3%,同时减轻客户端侧计算开销79%。     

A blockchain-based audit approach for encrypted data in federated learning

The development of data-driven artificial intelligence technology has given birth to a variety of big data applications. Data has become an essential factor to improve these applications. Federated learning, a privacy-preserving machine learning method, is proposed to leverage data from different data owners. It is typically used in conjunction with cryptographic methods, in which data owners train the global model by sharing encrypted model updates. However, data encryption makes it difficult to identify the quality of these model updates. Malicious data owners may launch attacks such as data poisoning and free-riding. To defend against such attacks, it is necessary to find an approach to audit encrypted model updates. In this paper, we propose a blockchain-based audit approach for encrypted gradients. It uses a behavior chain to record the encrypted gradients from data owners, and an audit chain to evaluate the gradients’ quality. Specifically, we propose a privacy-preserving homomorphic noise mechanism in which the noise of each gradient sums to zero after aggregation, ensuring the availability of aggregated gradient. In addition, we design a joint audit algorithm that can locate malicious data owners without decrypting individual gradients. Through security analysis and experimental evaluation, we demonstrate that our approach can defend against malicious gradient attacks in federated learning.     

基于联邦学习的本地化差分隐私机制研究

联邦学习与群体学习作为当前热门的分布式机器学习范式,前者能够保护用户数据不被第三方获得的前提下在服务器中实现模型参数共享计算,后者在无中心服务器的前提下利用区块链技术实现所有用户同等地聚合模型参数。但是,通过分析模型训练后的参数,如深度神经网络训练的权值,仍然可能泄露用户的隐私信息。目前,在联邦学习下运用本地化差分隐私(LDP)保护模型参数的方法层出不穷,但皆难以在较小的隐私预算和用户数量下缩小模型测试精度差。针对此问题,该文提出正负分段机制(PNPM),在聚合前对本地模型参数进行扰动。首先,证明了该机制满足严格的差分隐私定义,保证了算法的隐私性;其次分析了该机制能够在较少的用户数量下保证模型的精度,保证了机制的有效性;最后,在3种主流图像分类数据集上与其他最先进的方法在模型准确性、隐私保护方面进行了比较,表现出了较好的性能。     

Review on application progress of federated learning model and security hazard protection

Federated learning is a new type of distributed learning framework that allows multiple participants to share training results without revealing their data privacy. As data privacy becomes more important, it becomes difficult to collect data from multiple data owners to make machine learning predictions due to the lack of data security. Data is forced to be stored independently between companies, creating “data silos”. With the goal of safeguarding data privacy and security, the federated learning framework greatly expands the amount of training data, effectively improving the shortcomings of traditional machine learning and deep learning, and bringing AI algorithms closer to our reality. In the context of the current international data security issues, federated learning is developing rapidly and has gradually moved from the theoretical to the applied level. The paper first introduces the federated learning framework, analyzes its advantages, reviews the results of federated learning applications in industries such as communication and healthcare, then analyzes the pitfalls of federated learning and discusses the security issues that should be considered in applications, and finally looks into the future of federated learning and the application layer.     

Transient content caching and updating with modified harmony search for Internet of Things

Internet of Things (IoT) has emerged as one of the new use cases in the 5th Generation wireless networks. However, the transient nature of the data generated in IoT networks brings great challenges for content caching. In this paper, we study a joint content caching and updating strategy in IoT networks, taking both the energy consumption of the sensors and the freshness loss of the contents into account. In particular, we decide whether or not to cache the transient data and, if so, how often the servers should update their contents. We formulate this content caching and updating problem as a mixed 0–1 integer non-convex optimization programming, and devise a Harmony Search based content Caching and Updating (HSCU) algorithm, which is self-learning and derivative-free and hence stipulates no requirement on the relationship between the objective and variables. Finally, extensive simulation results verify the effectiveness of our proposed algorithm in terms of the achieved satisfaction ratio for content delivery, normalized energy consumption, and overall network utility, by comparing it with some baseline algorithms.     

Data encryption based blockchain and privacy preserving mechanisms towards big data

Blockchain is a key technique which can support Bitcoin. Blockchain is a decentralized infrastructure that uses chained data structure to verify and store data, and uses distributed node consensus mechanism to generate and update data. Blockchain has become a hot research topic since its attributes of decentralization, verifiability and anti-tampering. To stimulate the development of Blockchain, we conduct a comprehensive research on Blockchain. Specifically, we discuss various mainstream consensus mechanisms used in blockchain technology, and thoroughly analyze anonymity and privacy protection in digital currency. Aiming at data encryption mechanism, we discuss existing anonymity and privacy protection schemes. Our discussion can further promote the development of Blockchain.     

面向物联网隐私数据分析的分布式弹性网络回归学习算法

为了解决基于集中式算法的传统物联网数据分析处理方式易引发网络带宽压力过大、延迟过高以及数据隐私安全等问题,该文针对弹性网络回归这一典型的线性回归模型,提出一种面向物联网(IoT)的分布式学习算法。该算法基于交替方向乘子法(ADMM),将弹性网络回归目标优化问题分解为多个能够由物联网节点利用本地数据进行独立求解的子问题。不同于传统的集中式算法,该算法并不要求物联网节点将隐私数据上传至服务器进行训练,而仅仅传递本地训练的中间参数,再由服务器进行简单整合,以这样的协作方式经过多轮迭代获得最终结果。基于两个典型数据集的实验结果表明：该算法能够在几十轮迭代内快速收敛到最优解。相比于由单个节点独立训练模型的本地化算法,该算法提高了模型结果的有效性和准确性;相比于集中式算法,该算法在确保计算准确性和可扩展性的同时,可有效地保护个体隐私数据的安全性。     

基于物联网的井下人员定位算法

随着煤炭开采强度和深度的提高,物联网技术逐渐成为井下人员定位系统中的热点。此外,3G网络的不断发展也为井下人员的精确定位提供了强有力的支持。采用TD-SCDMA技术,在井下铺设TD基站,利用物联网技术完成井下节点的组网建设。在此基础上对传统的Chan算法和Taylor算法进行改进,充分利用TD-SCDMA技术的优势,提出一种混合数据融合定位算法,经仿真证明,提出的基于物联网的定位算法在一定程度上克服了煤矿井下恶劣环境的影响,大大提高了定位精度。     

面向物联网数据特征的信息中心网络缓存方案

将信息中心网络(ICN)应用到物联网(IoT)架构(ICN-IoT),可以有效地解决数据分发问题,提高数据的传输效率.但在ICN-IoT中,现有的缓存研究主要是在内容流行度或新鲜度等单一维度上实现缓存配置,无法适应海量和多态的物联网数据特征,导致缓存效率低.针对上述问题,该文首先分析了物联网数据特征,将数据分为周期性数...     

A group key exchange and secure data sharing based on privacy protection for federated learning in edge-cloud collaborative computing environment

Federated learning (FL) is widely used in internet of things (IoT) scenarios such as health research, automotive autopilot, and smart home systems. In the process of model training of FL, each round of model training requires rigorous decryption training and encryption uploading steps. The efficiency of FL is seriously affected by frequent encryption and decryption operations. A scheme of key computation and key management with high efficiency is urgently needed. Therefore, we propose a group key agreement technique to keep private information and confidential data from being leaked, which is used to encrypt and decrypt the transmitted data among IoT terminals. The key agreement scheme includes hidden attribute authentication, multipolicy access, and ciphertext storage. Key agreement is designed with edge-cloud collaborative network architecture. Firstly, the terminal generates its own public and private keys through the key algorithm then confirms the authenticity and mapping relationship of its private and public keys to the cloud server. Secondly, IoT terminals can confirm their cryptographic attributes to the cloud and obtain the permissions corresponding to each attribute by encrypting the attributes. The terminal uses these permissions to encrypt the FL model parameters and uploads the secret parameters to the edge server. Through the storage of the edge server, these ciphertext decryption parameters are shared with the other terminal models of FL. Finally, other terminal models are trained by downloading and decrypting the shared model parameters for the purpose of FL. The performance analysis shows that this model has a better performance in computational complexity and computational time compared with the cited literature.     

An adaptive resource sharing strategy for TDMA

A satellite-based TDMA network consisting of four stations within different rain climatic zones has been operated in the 20/30 GHz frequency range using a recently developed flexible TDMA system allowing for FEC code rate and transmission bit rate variation. In this paper a strategy is presented to counteract overall link degradations due to atmospheric attenuation by dynamic allocation of resources. A spare time slot within the TDMA frame as a ‘common resource’ for bit rate and code rate switching offers up to 12 dB gain, whereas up-link power control, as it is implemented in this configuration, can cope with fades of 8 dB at maximum. For an experimental network configuration the expected long-term performance in terms of system availability is estimated for a viable version of the resource sharing strategy. Thereby, a model to calculate the probability of concurrent attenuation at the individual earth-station sites (‘satellite based diversity’) has been applied and the resulting probability to exhaust the resources is considered as a function of the degrading correlation between attenuations. Simulations with measured data via a ‘channel simulator’ and satellite measurements during the summer months of 1994 with the adaptive TDMA system are planned to test the functionality of the fade countermeasure strategy. Long-term propagation measurements on large-scale site diversity are required to verify predictions on the effective utilization of common resources.     

Internet of Things Cloud Framework for Smart Homes

Smart appliances and renewable energy resources are becoming an integral part of smart homes. Nowadays, home appliances are communicating with each other with home gateways, using existing short-range home area network communication protocols such as ZigBee, Bluetooth, RFID, and WiFi. A Gateway allows homeowners and utilities to communicate remotely with the appliances via long-range communication networks such as GPRS, WiMax, LTE, and power liner carrier. This paper utilizes the Internet of Things (IoT) concepts to monitor and control home appliances. Moreover, this paper proposes a framework that enables the integration and the coordination of Human-to-Appliance, Utility-to-Appliance, and Appliance-to-Appliance. Utilizing the concepts of Internet of Things leads to one standard communication protocols, TCP/IPV6, which overcomes the many diverse home area networks and neighborhood area networks protocols. This work proposes a cloud based framework that enables the IoTs integration and supports the coordination between devices, as well as with device-human interaction. A prototype is designed, implemented, and tested to validate the proposed solution.     

面向智能电网的物联网信息聚合技术

物联网应用于智能电网是信息通信技术发展到一定阶段的必然结果,利用物联网技术将能有效整合电力系统基础设施资源,提高电力系统信息化水平,改善现有电力系统基础设施的利用效率。本文针对物联网技术和我国智能电网建设规划,研究面向智能电网应用的物联网网络架构及关键技术,总结了技术特点。在阐明网络架构的基础上,进一步针对智能电网应用中海量设备终端和海量采集信息的特点,详细论述物联网信息聚合技术,分析信息聚合技术带来的网络收益,提出信息聚合技术基本功能框架及实现方式。物联网信息聚合技术在采集原始数据的同时进行大量的信息处理和计算,从海量的、杂乱无章、难以理解的原始数据中抽取并推导出对于智能电网一体化管理平台具有特定意义和判决参考价值的数据,并且能够降低网络数据传输总量、减少网络拥塞发生、提高网络性能,是物联网发展的重要技术方向之一。本文针对智能电网目前相对薄弱的配用电环节提出配变电设备监测物联网的主要功能与信息聚合方案。     

A survey on communication protocols and performance evaluations for Internet of Things

The Internet of Things (IoT) is a large-scale network of devices capable of sensing, data processing, and communicating with each other through different communication protocols. In today's technology ecosystem, IoT interacts with many application areas such as smart city, smart building, security, traffic, remote monitoring, health, energy, disaster, agriculture, industry. The IoT network in these scenarios comprises tiny devices, gateways, and cloud platforms. An IoT network is able to keep these fundamental components in transmission under many conditions with lightweight communication protocols taking into account the limited hardware features (memory, processor, energy, etc.) of tiny devices. These lightweight communication protocols affect the network traffic, reliability, bandwidth, and energy consumption of the IoT application. Therefore, determining the most proper communication protocol for application developers emerges as an important engineering problem. This paper presents a straightforward overview of the lightweight communication protocols, technological advancements in application layer for the IoT ecosystem. The survey then analyzes various recent lightweight communication protocols and reviews their strengths and limitations. In addition, the paper explains the experimental comparison of Constrained Applications Protocol (CoAP), Message Queuing Telemetry (MQTT), and WebSocket protocols, more convenient for tiny IoT devices. Finally, we discuss future research directions of communication protocols for IoT.     

Machine learning-based clustering protocols for Internet of Things networks: An overview

The Internet of Things (IoT) continues to expand the current Internet, opening the door to a wide range of novel applications. The increasing volume of the IoT requires effective strategies to overcome its challenges. Machine Learning (ML) has led to a growing technology that enables computers to solve problems without the need for knowledge of their intricate details. Over the past years, various ML techniques have been used to efficiently manage IoT networks. Clustering is a technique that has proven its performance in the networking domain. Many works in the literature have studied ML-based clustering methods for IoT networks, including their main properties, characteristics, underlying technologies, and open issues. In this paper, we focus on topology-centered ML-based clustering protocols for IoT networks. Specifically, we investigate the potential benefits of adopting the clustering approach to address several IoT challenges. Moreover, we provide a comprehensive taxonomy of ML-based clustering algorithms for IoT networks. Finally, we statistically analyze the incorporation of ML techniques for clustering in various IoT systems and highlight the related open issues.     

物联网异构环境中面向服务的中间件

A great number of sensor technologies are applied in the Internet of Things (IoT) currently and more are emerging,which makes the IoT a heterogeneous network. This paper discusses the convergence and integration problem in IoT. A Service-O-riented Middleware for Heterogeneous Environment (SOMHE) in IoT is proposed. The purpose of the middleware is to shield the difference between protocols in the sensor layers such as Radio Frequency Identification (RFID) and ZigBee by defining the data conversion and mapping model. A Web service interface is supplied by this middleware, thus the complexity of high level application development can be reduced greatly. The feasibility and reliability of this middleware is verified by a demonstration system.     

异构物联网下资源高效的分层协同联邦学习方法

物联网(IoT)设备资源存在高度异构性,严重影响联邦学习(FL)的训练时间和精度。已有研究未充分考虑物联网设备资源的异构性,且缺乏异构设备间协同训练机制的设计,导致训练效果有限且设备的资源利用率较低。为此,该文提出资源高效的分层协同联邦学习方法(HCFL),设计了端边云分层混合聚合机制,考虑边缘服务器的差异化参数聚合频率,提出自适应异步加权聚合方法,提高模型参数聚合效率。提出资源重均衡的客户端选择算法,考虑模型精度与数据分布特征动态选取客户端,缓解资源异构性对联邦学习性能的影响。设计自组织联邦协同训练算法,充分利用空闲物联网设备资源加速联邦学习训练进程。仿真结果表明,在不同资源异构状态下,与基线方法相比,模型训练时间平均降低15％,模型精度平均提高6％,设备平均资源利用率提高52％。     

基于混合隐私的区块链高效模型协同训练共享方案

针对海量数据下,基于区块链的联邦学习数据共享平台面临的效率低下和隐私泄露问题,该文提出基于混合隐私的区块链高效模型协同训练共享方案。在该方案中,首先根据欧氏距离设计了一种基于相似度的训练成员选择算法来选择训练成员,组成联邦社区,即通过选取少量的高匹配训练节点来提高训练的效率和效果。然后,结合阈值同态加密和差分隐私,设计一种基于混合隐私技术的模型协同训练共享方案来保证训练和共享过程中的隐私性。实验结果和系统实现表明,所提方案可以在保证训练结果准确率的情况下,实现高效训练和隐私保护下的数据共享。     

低轨卫星星座物联网业务量建模

随着物联网(IoT)规模的不断发展,其业务需求呈现出多样化、全球化的趋势。针对地面物联网无法覆盖全球的缺点,卫星物联网尤其是低轨卫星星座(LEOSC)物联网可以有效地为地面物联网提供覆盖性能上的补充和延伸。由于低轨卫星星座物联网系统广覆盖、高动态的特点,其业务量统计特性需要考虑到环境因素造成的影响,这导致其业务量分布与...