Search

In this paper, we present a garbage image classification framework to tackle the waste sorting problem which besets residents around the world every day. The proposed framework consists of two modules, a convolutional neural network backbone transferred from the ImageNet classification task and a customized network header designed for the garbage image classification task. To friendly deploy into mobile devices, the proposed method makes an artful tradeoff between classification accuracy and running efficiency. The proposed framework yields 95.62% online classification accuracy on the test dataset provided by Huawei cloud with 95 ms per image inference time occupying 897 Megabytes GPU memory.

With the gradual progress of cloud computing, big data, network virtualization and other network technology, exponential growth of data makes traditional network show its weakness completely. Such as inefficiency of data forwarding, poor agility of network deployment and so on. SDN(Software Defined Networking) separates data forwarding from logic control and makes network programmable to improve utilization of network resources, and then, there are efficiency of data forwarding and agility of network deployment. Compared to traditional network, SDN network is more in line with the future network for its characteristic. However, SDN is facing some severe problems too. Like flow table congestion and network security problems. In SDN network, OpenFlow switches can only contain 3000 flow entries which means flow table resources are really rare. Thus, we come out with a strategy of flow table optimizing. We choose a number of switches based on betweenness centrality as the station on "bus route" and issue the least flow entry to realize the whole network working.

Cloud computing is a new paradigm, which provides low-cost and effective outsourced data storage service. People are used to storing personal data in cloud server. E-Health system (EHS) privacy should be protected, because it is national security for citizen privacy. Personal Health Record (PHR) is the core of EHS that should be protected. Thus, how to efficiently store, access and share these data is critical. Attribute-based encryption (ABE) is a new public key encryption based on users’ attributes. In this paper, we present a new method to realize a secure fine-grained access control to PHRs, which is based on emerging ABE primitives. In more details, PHR owners divide the PHR data in terms of the privacy levels. A key-policy ABE (KP-ABE) is utilized to provide a fine-grained access control storage system for outsourced sensitive data. It can also provide efficient user revocation by using the timestamp in the private key. Security analysis shows that our construction achieves the data confiden...

Network-attached storage (NAS) provides cyberphysical systems (CPS) with the scalable, efficient, and reliable backing storage, such as the mobile virtual desktop based on cloud infrastructure. Within this storage architecture, virtual machine (VM) instances running in the NAS client usually receive data from the complex physical world and then persist them in the neat cyberspace in the NAS server. In this paper, we propose Triple-L to improve VM disk I/O performance in the NAS architecture. According to the specific storage semantic, Triple-L decouples the VM image file into several subfiles at the host layer and then selectively moves them into the NAS clients. In such a way, a VM disk I/O request may be proceeded locally in the NAS client, instead of walking the external networking path repetitively between NAS server and client. We have implemented Triple-L in a Xen-based NAS system. An accessory solution for dealing with storage failure and VM live migration on Triple-L is also discussed and evaluated. The experimental result shows that our work can effectively improve the disk I/O performance of VMs. Meanwhile, it brings moderate overhead for VM live migration.

Storage class memory (SCM) has the potential to revolutionize the memory landscape by its non-volatile and byte-addressable properties. However, there is little published work about exploring its usage for modern virtualized cloud infrastructure. We propose SCM-vWrite, a novel architecture designed around SCM, to ease the performance interference of virtualized storage subsystem. Through a case study on a typical virtualized cloud system, we first describe why current writeback manners are not suitable for a virtualized environment, then design and implement SCM-vWrite to improve this problem. We also use typical benchmarks and realistic workloads to evaluate its performance. Compared with the traditional method on a conventional architecture, the experimental result shows that SCM-vWrite can coordinate the writeback flows more effectively among multiple co-located guest operating systems, achieving a better disk I/O performance without any loss of reliability.

Cloud computing offers a cheap and efficient solution for the deployment of web applications. It results in a big increase of the number of service provider. Users hold multiple identities for using services from different domains. The openness of public clouds requires the authentication system to accept user identities from various domains and to support hybrid authentication protocols. This work proposes a cross-domain single sign-on mechanism to address the preceding issues and makes a formal mathematical model to analyze the security issues of the proposed mechanism's authentication architecture; furthermore, an algorithm is proposed to detect the authentication architecture's weak vertex whose failure would lead to a partial failure in the architecture. The proposed mechanism allows service providers to verify user identities in a decentralized way and allows users to unify their identities from various domains in a safe way. The verification process used in this mechanism is able to support hybrid authentication protocols as well as to accelerate the verification of credentials by eliminating single point of failure and single-point bottleneck. Copyright © 2015John Wiley & Sons, Ltd.

Social networks have experienced exponential growth in membership and have become a hotspot for research in recent years. It helps users manage relations by establishing new relations and maintaining existing relations. On the basis of social networks' research, to encourage communication between scholars and facilitate management of academic information and academic relations, we built the Scholar-Oriented Social Network Cloud (SOSN) that is an academic information-centric social network. SOSN extracts academic information from various web sources on the Internet, and provides an application model for the social interaction and the semantic description of all related information. SOSN works as follows. Firstly, an academic search cloud is created that can provides academic search services according to users' web context. Then SOSN extracts public academic information from various literature databases and search engines on the web using the academic extracting services; secondly, SOSN devises an application model in the domain of scholar social network, which is used to represent the complex relations of entities in the Scholar-Oriented Social Network Cloud; thirdly, based on FOAF (Friend of a Friend), MarcOnt ontology, FRBR (Functional Requirements for Bibliographic Records) and SWAP (Scholarly Works Application Profile) academic semantic project, SOSN defines Scholar, AcademicWork, AcademicTeam ontology, etc. using RDF language according to semantic web technology and implements the semantic description of Scholar-Oriented Social Network Cloud.

Cloud computing has become a hot topic both in research and in industry, and when making decisions on deploying/adopting cloud computing related solutions, security has always been a major concern. This article summarizes security related issues in cloud computing and proposes five service deployment models to address these issues. The proposed models provide different security related features to address different requirements and scenarios and can serve as reference models for deployment.

This is a copy of the author 's final draft version of an article published in the journal Multimedia tools and applications. The final publication is available at Springer via http://dx.doi.org/10.1007/s11042-013-1829-6 With the development of cloud computing, electronic health record (EHR) system has appeared in the form of patient-centric, in which patients store their personal health records (PHRs) at a remote cloud server and selectively share them with physicians for convenient medical care. Although the newly emerged form has many advantages over traditional client-server model, it inevitably introduces patients' concerns on the privacy of their PHRs due to the fact that cloud servers are very likely to be in a different trusted domain from that of the patients. In this paper, aiming at allowing for efficient storing and sharing PHRs and also eliminating patients' worries about PHR privacy, we design a secure cloud-based EHR system, which guarantees security and privacy of medical data stored in the cloud, relying on cryptographic primitive but not the full trust over cloud servers. Based on our proposed basic EHR system, we provide several extensions including adding searchability, supporting revocation functionality and enabling efficient local decryption, which fills the gap between theoretical proposal and practical application.

IaaS cloud converts physical resources into resource pools. The pool oriented resource management model requires transparency of the underlying physical resources, as well as the on-demand consumption of IT services and the trust verification of the resources from cloud users. A viable way is by creating trusted clusters that consist of trusted physical machines, with strict membership management of these trusted clusters, confining IT services to be hosted within trusted clusters. This paper proposes a trusted cluster scheme which is based on a dynamic group signature scheme. The scheme fits into the pool oriented trust management for cloud computing.

IaaS encourages pooled resource management model, which provides transparency on the management and provision of IT resources. The transparency, hiding physical details of the underlying resources, makes it difficult for cloud users/services to identify trusted resources for service deployment, resulting in potential risks of deploying critical services on untrusted resources. This paper proposes a pool oriented trust management mechanism for cloud infrastructures, allowing the construction and identification of trusted clusters consisted of trusted resources, with strict membership management to accept only trusted physical resources. Resources of a trusted cluster expose identical trust properties/attributes to cloud users, enabling users to verify the trust on the resources without the need of identifying individual physical resource. Hence, service deployment and migration can be augmented with the above trust verification to ensure that services are always deployed on trusted resources.

IaaS encourages pooled resource management model, which provides transparency on the management and provision of IT resources. The transparency, hiding physical details of the underlying resources, makes it difficult for cloud users/services to identify trusted resources for service deployment, resulting in potential risks of deploying critical services on untrusted resources. This paper proposes a pool oriented trust management mechanism for cloud infrastructures, allowing the construction and identification of trusted clusters consisted of trusted resources, with strict membership management to accept only trusted physical resources. Resources of a trusted cluster expose identical trust properties/attributes to cloud users, enabling users to verify the trust on the resources without the need of identifying individual physical resource. Hence, service deployment and migration can be augmented with the above trust verification to ensure that services are always deployed on trusted resources.

Platform as a service (PaaS) is a cloud computing service model that provides a computing platform and a solution stack as an on-demand service, allowing users to create, deploy and control their own cloud services without building and managing their own computing platforms. PaaS providers provide the networks, servers and storages alongside with the PaaS platform. Though cloud computing is getting prevalence in IT, security, in particular privacy, has incurred the most concerns from users. Using a cloud service, a user has no privilege in managing the underlying computing platform nor the underlying resource and infrastructure, leading to the situation that a user has no way to monitor cloud services' behavior to protect the user's privacy. This paper proposes a privacy enhancing framework on PaaS for detecting the privacy violating behavior and protecting user's information instantly by enforcing related protection actions. The proposed framework allows customized security policies and behavior analysis models, enabling users to impose application oriented privacy monitoring mechanisms.

This paper describes a cryptographic protocol for storing and processing data in a Cloud Computing setting, where users need not place absolute trust in the various Cloud Processing providers. This is achieved by distributing data among various Cloud Storage providers in such a manner that an individual data item does not divulge useful information about its owner, and only re-assembling data when it needs to be processed or returned to the user.

This paper applies a divide-and-conquer approach to achieve confidentiality control in Cloud Computing. We sketch how a Redundant Array of Independent Net-storages (RAIN) for Cloud Computing can be designed using techniques originally intended for other purposes. The RAIN approach splits data into segments and distributes segments onto multiple providers. By keeping the relationships between the distributed segments private, the original data cannot be re-assembled. Further, with each segment small enough, each segment discloses no meaningful information to others. Hence RAIN is able to ensure the confidentiality of data stored on clouds.

Cloud storage services are gaining more and more attention. Surveys suggest that the confidentiality issue is one of the major obstacles for users to use cloud storage services to keep sensitive data. This paper proposes to deploy a Redundant Array of Independent Net-storages (RAIN) for confidentiality control in Cloud Computing. The RAIN approach splits data into segments and distributes segments onto multiple storage providers, without having to trust each provider. By keeping the distribution of segments and the relationships between the distributed segments private, the original data cannot be reassembled. When the segments are small enough, each segment discloses no meaningful information to others. Hence RAIN is able to ensure the confidentiality of data stored on clouds. A formal model of the proposed approach has been developed to articulate the process. Security analysis has been performed, indicating that the proposed approach can implement confidentiality protection without the need of encrypting the data.

Cloud computing is an emerging computing paradigm in which IT resources and capacities are provided as services over the Internet. Promising as it is, this paradigm also brings forth new challenges for data security and access control when users outsource sensitive data for sharing on cloud servers, which are likely outside of the same trust domain of data owners. To maintain the confidentiality of, sensitive user data against untrusted servers, existing work usually apply cryptographic methods by disclosing data decryption keys only to authorized users. However, in doing so, these solutions inevitably introduce heavy computation overhead on the data owner for key distribution and data management when fine-grained data access control is desired, and thus do not scale well. In this paper, we present a way to implement, scalable and fine-grained access control systems based on attribute-based encryption (ABE). For the purpose of secure access control in cloud computing, the prevention of illegal key sharing among colluding users is missing from the existing access control systems based on ABE. This paper addresses this challenging open issue by defining and enforcing access policies based on data attributes and implementing user accountability by using traitor tracing. Furthermore, both the user grant and revocation are efficiently supported by using the broadcast encryption technique. Extensive analysis shows that the proposed scheme is highly efficient and provably secure under existing security models.

Cloud computing has been acknowledged as one of the prevaling models for providing IT capacities. The off-premises computing paradigm that comes with cloud computing has incurred great concerns on the security of data, especially the integrity and confidentiality of data, as cloud service providers may have complete control on the computing infrastructure that underpins the services. This makes it difficult to share data via cloud providers where data should be confidential to the providers and only authorized users should be allowed to access the data. This work aims to construct a system for trusted data sharing through untrusted cloud providers, to address the above mentioned issue. The constructed system can imperatively impose the access control policies of data owners, preventing the cloud storage providers from unauthorized access and making illegal authorization to access the data.

Cloud computing has become a popular choice as an alternative to investing new IT systems. When making decisions on adopting cloud computing related solutions, security has always been a major concern. This article summarizes security concerns in cloud computing and proposes five service deployment models to ease these concerns. The proposed models provide different security related features to address different requirements and scenarios and can serve as reference models for deployment. Deployment models: Towards eliminating security concerns from cloud computing

More and more companies begin to provide different kinds of cloud computing services for Internet users at the same time these services also bring some security problems. Currently the majority of cloud computing systems provide digital identity for users to access their services, this will bring some inconvenience for a hybrid cloud that includes multiple private clouds and/or public clouds. Today most cloud computing system use asymmetric and traditional public key cryptography to provide data security and mutual authentication. Identity-based cryptography has some attraction characteristics that seem to fit well the requirements of cloud computing. In this paper, by adopting federated identity management together with hierarchical identity-based cryptography (HIBC), not only the key distribution but also the mutual authentication can be simplified in the cloud.

Users see that cloud computing delivers elastic computing services to users based on their needs. Cloud computing service providers must make sure enough resources are provided to meet users' demand, by either the provision of more than enough resource, or the provision of just-enough resource. This paper investigates the growth of the user set of a cloud computing service from statistic's point of view. The investigation leads to a simply model on the growth of the system in terms of users. This model provides a simple way to compute the scale of a system at a given time, thus allowing a cloud computing service provider to predict the system's scale based on the number of users and plan for the infrastructure deployment.

This article describes how a Redundant Array of Independent Net-storages (RAIN) can be deployed for confidentiality control in Cloud Computing. The RAIN approach splits data into segments and distributes segments between multiple storage providers; by keeping the distribution of segments and the relationships between the distributed segments private, the original data cannot be re-assembled by an observer. As long as each segment is small enough, an individual segment discloses no meaningful information to others, and hence RAIN is able to ensure the confidentiality of data stored in the clouds. We describe the inter-cloud communication protocol, and present a formal model, security analysis, and simulation results.