Multi-key privacy-preserving deep learning in cloud computing

Deep learning has attracted a lot of attention and has been applied successfully in many areas such as bioinformatics, imaging processing, game playing and computer security etc. On the other hand, deep learning usually requires a lot of training data which may not be provided by a sole owner. As the volume of data gets huge, it is common for users to store their data in a third-party cloud. Due to the confidentiality of the data, data are usually stored in encrypted form. To apply deep learning to these datasets owned by multiple data owners on cloud, we need to tackle two challenges: (i) the data are encrypted with different keys, all operations including intermediate results must be secure; and (ii) the computational cost and the communication cost of the data owner(s) should be kept minimal. In our work, we propose two schemes to solve the above problems. We first present a basic scheme based on multi-key fully homomorphic encryption (MK-FHE), then we propose an advanced scheme based on a hybrid structure by combining the double decryption mechanism and fully homomorphic encryption (FHE). We also prove that these two multi-key privacy-preserving deep learning schemes over encrypted data are secure.     

A green energy-efficient scheduling algorithm using the DVFS technique for cloud datacenters

Information and communication technology (ICT) has a profound impact on environment because of its large amount of CO₂ emissions. In the past years, the research field of “green” and low power consumption networking infrastructures is of great importance for both service/network providers and equipment manufacturers. An emerging technology called Cloud computing can increase the utilization and efficiency of hardware equipment. The job scheduler is needed by a cloud datacenter to arrange resources for executing jobs. In this paper, we propose a scheduling algorithm for the cloud datacenter with a dynamic voltage frequency scaling technique. Our scheduling algorithm can efficiently increase resource utilization; hence, it can decrease the energy consumption for executing jobs. Experimental results show that our scheme can reduce more energy consumption than other schemes do. The performance of executing jobs is not sacrificed in our scheme. We provide a green energy-efficient scheduling algorithm using the DVFS technique for Cloud computing datacenters.     

云计算架构中恶意代码入侵自动监测系统设计

为了解决云计算架构中恶意代码以各种形式入侵产生损害,不能及时发现、维护而造成云计算架构安全性能降低,无法正常使用的问题,建立一套基于BP神经网络的入侵监测系统,实现对云计算架构中恶意代码入侵的自动监测,对及时监测入侵恶意代码及有效增加云计算架构安全有这直接而又重要作用;系统以STM32F103ZET6为主控芯片构建MUC主控单元,并通过EZ-USB FX2 USB2.0控制芯片将各个模块与其相连;采用LM2575系列的稳压器,为系统提供电源;软件设计过程中,采用BP神经网络法计算各恶意代码入侵的输出值,降低监测误差;通过实验测试表明,该系统可实现云计算架构中入侵恶意代码的自动监测功能,且具有扩展性强、操作方便等特点,对云计算架构的使用安全性具有重要的应用价值。     

云计算中的入侵检测模型

本文提出了一种云环境下的网络安全处理模型,模型中的每台云服务器都拥有自己的入侵检测系统,并且所有的服务器共享一个异常管理平台,该平台负责报警信息的接收、处理和日志管理.模型采用报警级别动态调整技术和攻击信息共享方法,最大限度地降低了漏报率和服务器遭受同种攻击的可能性,有效提高了检测效率和系统安全水平.     

Packet aggregation based network I/O virtualization for cloud computing

Virtualization is a key technology to enable cloud computing. Driver domain based model for network virtualization offers isolation and high levels of flexibility. However, it suffers from poor performance and lacks scalability. In this paper, we evaluate networking performance of virtual machines within Xen. The I/O channel transferring packets between the driver domain and the virtual machines is shown to be the bottleneck. To overcome this limitation, we proposed a packet aggregation based mechanism to transfer packets from the driver domain to the virtual machines. Packet aggregation, combined with an efficient core allocation, allows virtual machines throughput to scale up by 700%, while minimizing both memory and CPU consumption. Besides, aggregation impact on packets delay and jitter remains acceptable. Hence, the proposed I/O virtualization model satisfies infrastructure providers to offer Cloud computing services.     

智能电网中虚拟化云计算的应用和安全技术分析

智能电网符合当前需求,意义重大。首先简单介绍了云计算和智能电网,并对云计算在智能电网中的应用做了阐述,然后主要对云计算的安全技术进行了分析。     

Review:Data center network architecture in cloud computing:review,taxonomy, and open research issues

The data center network(DCN), which is an important component of data centers, consists of a large number of hosted servers and switches connected with high speed communication links. A DCN enables the deployment of resources centralization and on-demand access of the information and services of data centers to users. In recent years, the scale of the DCN has constantly increased with the widespread use of cloud-based services and the unprecedented amount of data delivery in/between data centers, whereas the traditional DCN architecture lacks aggregate bandwidth, scalability, and cost effectiveness for coping with the increasing demands of tenants in accessing the services of cloud data centers. Therefore, the design of a novel DCN architecture with the features of scalability, low cost, robustness, and energy conservation is required. This paper reviews the recent research findings and technologies of DCN architectures to identify the issues in the existing DCN architectures for cloud computing. We develop a taxonomy for the classification of the current DCN architectures, and also qualitatively analyze the traditional and contemporary DCN architectures. Moreover, the DCN architectures are compared on the basis of the significant characteristics, such as bandwidth, fault tolerance, scalability, overhead, and deployment cost. Finally, we put forward open research issues in the deployment of scalable, low-cost, robust, and energy-efficient DCN architecture, for data centers in computational clouds.     

Collaborative design in the era of cloud computing

The paper describes the application of the latest Information Technologies in business processes such as design and manufacturing. More specifically it examines the use of cloud computing in the mechanical drawing and design process of an enterprise. It proposes a specific architecture with different servers, for the implementation of a collaborative cloud based Design system. Finally as an application example, it compares the operating cost of an industry’s design department before and after the use of the proposed system. This example uses a private cloud deployment model so that the comparison of the operating cost would be feasible. While public cloud may offer more functionality and economy, private cloud is best suitable to make conclusions and comparison between on-premise and cloud operation, because all of the cost is handled by the organization that uses it.     

Empirical prediction models for adaptive resource provisioning in the cloud

Cloud computing allows dynamic resource scaling for enterprise online transaction systems, one of the key characteristics that differentiates the cloud from the traditional computing paradigm. However, initializing a new virtual instance in a cloud is not instantaneous; cloud hosting platforms introduce several minutes delay in the hardware resource allocation. In this paper, we develop prediction-based resource measurement and provisioning strategies using Neural Network and Linear Regression to satisfy upcoming resource demands.Experimental results demonstrate that the proposed technique offers more adaptive resource management for applications hosted in the cloud environment, an important mechanism to achieve on-demand resource allocation in the cloud.     

Uncertainty quantification through the Monte Carlo method in a cloud computing setting

The Monte Carlo (MC) method is the most common technique used for uncertainty quantification, due to its simplicity and good statistical results. However, its computational cost is extremely high, and, in many cases, prohibitive. Fortunately, the MC algorithm is easily parallelizable, which allows its use in simulations where the computation of a single realization is very costly. This work presents a methodology for the parallelization of the MC method, in the context of cloud computing. This strategy is based on the MapReduce paradigm, and allows an efficient distribution of tasks in the cloud. This methodology is illustrated on a problem of structural dynamics that is subject to uncertainties. The results show that the technique is capable of producing good results concerning statistical moments of low order. It is shown that even a simple problem may require many realizations for convergence of histograms, which makes the cloud computing strategy very attractive (due to its high scalability capacity and low-cost). Additionally, the results regarding the time of processing and storage space usage allow one to qualify this new methodology as a solution for simulations that require a number of MC realizations beyond the standard.     

Cost-oriented proactive fault tolerance approach to high performance computing (HPC) in the cloud

Cloud computing offers new computing paradigms, capacity and flexible solutions to high performance computing (HPC) applications. For example, Hardware as a Service (HaaS) allows users to provide a large number of virtual machines (VMs) for computation-intensive applications using the HaaS model. Due to the large number of VMs and electronic components in HPC system in the cloud, any fault during the execution would result in re-running the applications, which will cost time, money and energy. In this paper we presented a proactive fault tolerance (FT) approach to HPC systems in the cloud to reduce the wall-clock execution time and dollar cost in the presence of faults. We also developed a generic FT algorithm for HPC systems in the cloud. Our algorithm does not rely on a spare node prior to prediction of a failure. We also developed a cost model for executing computation-intensive applications on HPC systems in the cloud. We analysed the dollar cost of provisioning spare nodes and checkpointing FT to assess the value of our approach. Our experimental results obtained from a real cloud execution environment show that the wall-clock execution time and cost of running computation-intensive applications in cloud can be reduced by as much as 30%. The frequency of checkpointing of computation-intensive applications can be reduced up to 50% with our FT approach for HPC in the cloud compared with current FT approaches.     

Empowering village doctors and enhancing rural healthcare using cloud computing in a rural area of mainland China

Background

China's healthcare system often struggles to meet the needs of its 900 million people living in rural areas due to major challenges in preventive medicine and management of chronic diseases. Here we address some of these challenges by equipping village doctors (ViDs) with Health Information Technology and developing an electronic health record (EHR) system which collects individual patient information electronically to aid with implementation of chronic disease management programs.

Methods

An EHR system based on a cloud-computing architecture was developed and deployed in Xilingol county of Inner Mongolia using various computing resources (hardware and software) to deliver services over the health network using Internet when available. The system supports the work at all levels of the healthcare system, including the work of ViDs in rural areas. An analysis done on 291,087 EHRs created from November 2008 to June 2011 evaluated the impact the EHR system has on preventive medicine and chronic disease management programs in rural China.

Results

From 2008 to 2011 health records were created for 291,087 (26.25%) from 1,108,951 total Xilingol residents with 10,240 cases of hypertension and 1152 cases of diabetes diagnosed and registered. Furthermore, 2945 hypertensive and 305 diabetic patients enrolled in follow-up. Implementing the EHR system revealed a high rate of cholecystectomies leading to investigations and findings of drinking water contaminated with metals. Measures were taken to inform the population and clean drinking water was supplied.

Conclusions

The cloud-based EHR approach improved the care provision for ViDs in rural China and increased the efficiency of the healthcare system to monitor the health status of the population and to manage preventive care efforts. It also helped discover contaminated water in one of the project areas revealing further benefits if the system is expanded and improved.     

混合信号处理器MSP58C80／MSP58C20及其应用

ＳＰ５８Ｃ８０／ＭＳＰ５８Ｃ２０混合信号处理器，具有Ｓｉｇｍａ－Ｄｅｌｔａ编码解码器（ＣＯＤＥＣ），内置掩模式编程只读存储器，具有４８ｋｂｐｓ压缩率，在外部微控制器（ＭＣＵ）驱动下，可完成信息的存储、速览、删除、重播等功能。本文对ＭＳＰ５８Ｃ８０／ＭＳＰ５８Ｃ２０的工作原理、特点及外部接口，控制和应用等作了详细的讨论。     

Observations of achievement and motivation in using cloud computing driven CAD: Comparison of college students with high school and vocational high school backgrounds

Cloud computing technology has matured as it has been integrated with every kind of digitalization processes. It offers numerous advantages for data and software sharing, and thus making the management of complex IT systems much simpler. For education in engineering, cloud computing even provides students with versatile and ubiquitous access to software commonly used in the field without having to step into an actual computer lab. Our study analyzed learning attitudes and academic performances induced by the utilization of resources driven by cloud computing technologies. Comparisons were made between college students with high school and vocational high school backgrounds. One hundred and thirty-two students who took the computer-aided designing (CAD) course participated in the study. Technology Acceptance Model (TAM) was used as the fundamental framework. Open-ended sets of questionnaires were designed to measure academic performance and causal attributions; the results indicated no significant differences in the cognitive domain between the two groups of students, though it is not so in both the psychomotor and the affective domains. College students with vocational high school background appeared to possess higher learning motivation in CAD applications.     

Adaptive Probabilistic Behavioural Learning System for the effective behavioural decision in cloud trading negotiation market

In cloud e-commerce application, building an automated negotiation strategy by understanding the uncertain information of the opponent preferences, utilities, and tactics is highly challenging. The key issue is to analyse and predict the uncertain behaviour of the opponent tactics to suggest the appropriate counter tactics that can reach maximum consensus. To handle such uncertain information, negotiation strategies follow several tactics with and without learning ability. Strategies without learning ability are restricted to negotiate with the opponent having only deterministic behaviour. To overcome this problem most researchers exploited the negotiation strategies with fixed learning ability using Bayesian learning, neural network learning, and genetic tactics. These tactics can learn the opponent’s behaviour and cannot guarantee to generate suitable counter-offer for all offers submitted by the opponent cloud service provider. This limitation motivates to propose a novel Adaptive Probabilistic Behavioural Learning System for managing the opponent having unpredictable random behaviours. The proposed Adaptive Probabilistic Behavioural Learning System contains a Behavioural Inference Engine to analyse the sequence of negotiation offer received by the broker for effectively learning the opponent’s behaviour over several stages of negotiation process. It also formulates the multi-stage Markov decision problem to suggest the broker with appropriate counter-offer behavioural tactics generation based on the adaptive probabilistic decision taken over the corresponding negotiation stage. Therefore, this research work can outperform the existing fixed behavioural learning tactics and hence maximize the utility value and success rate of negotiating parties without any break-off.     

Neighborhood size selection in the k-nearest-neighbor rule using statistical confidence

The k-nearest-neighbor rule is one of the most attractive pattern classification algorithms. In practice, the choice of k is determined by the cross-validation method. In this work, we propose a new method for neighborhood size selection that is based on the concept of statistical confidence. We define the confidence associated with a decision that is made by the majority rule from a finite number of observations and use it as a criterion to determine the number of nearest neighbors needed. The new algorithm is tested on several real-world datasets and yields results comparable to the k-nearest-neighbor rule. However, in contrast to the k-nearest-neighbor rule that uses a fixed number of nearest neighbors throughout the feature space, our method locally adjusts the number of nearest neighbors until a satisfactory level of confidence is reached. In addition, the statistical confidence provides a natural way to balance the trade-off between the reject rate and the error rate by excluding patterns that have low confidence levels. We believe that this property of our method can be of great importance in applications where the confidence with which a decision is made is equally or more important than the overall error rate.     

Time‐out/time‐in: the dynamics of everyday experiential computing devices

In everyday life, the role of computing devices alternates between the ordinary and mundane, the un‐reflected and the extraordinary. To better understand the process through which the relationship between computing devices, users and context changes in everyday life, we apply a distinction between time‐in and time‐out use. Time‐in technology use coincides and co‐exists within the flow of ordinary life, while time‐out use entails ‘taking time out’ of everyday life to accomplish a circumscribed task or engage reflectively in a particular experience. We apply a theoretically informed grounded approach to data collected through a longitudinal field study of smartphone users during a 6‐month period. We analysed the data based on the concept of time‐in/out and show the dynamics in the experience of a device that changes from the ‘extraordinary’ to the ‘ordinary’ over time. We also provide a vocabulary that describes this relationship as stages resembling the one between a couple, which evolves from an early love affair, to being married and to growing old together. By repurposing the time‐in/out distinction from its origin in media studies, this paper marks a move that allows the distinction to be applied to understanding the use and dynamic becoming of computing devices over time.     

A new method for trust and reputation evaluation in the cloud environments using the recommendations of opinion leaders' entities and removing the effect of troll entities

Trust in the cloud environment is not written into an agreement and is something earned. In any trust evaluation mechanism, opinion leaders are the entities influencing the behaviors or attitudes of others, this makes them to be trustworthy, valid among other characteristics. On the other hand, trolls are the entities posting incorrect and unreal comments; therefore, their effect must be removed. This paper evaluates the trust by considering the influence of opinion leaders on other entities and removing the troll entities’ effect in the cloud environment. Trust value is evaluated using five parameters; availability, reliability, data integrity, identity and capability. Also, we propose a method for opinion leaders and troll entity identification using three topological metrics, including input-degree, output-degree and reputation measures. The method being evaluated in various situation where shows the results of accuracy by removing the effect of troll entities and the advice of opinion leaders.