Weibo is the Twitter counterpart in China that has attracted hundreds of millions of users. We crawled an almost complete Weibo user network that contains 222 million users and 27 billion links in 2013. This paper analyzes the structural properties of this network, and compares it with a Twitter user network. The topological properties we studied include the degree distributions, connected components, distance distributions, reciprocity,clustering coefficient, Page Rank centrality, and degree assortativity. We find that Weibo users have a higher diversity index, higher Gini index, but a lower reciprocity and clustering coefficient for most of the nodes. A surprising observation is that the reciprocity of Weibo is only about a quarter of the reciprocity of the Twitter user network. We also show that Weibo adoption rate correlates with economic development positively, and Weibo network can be used to quantify the connections between provinces and regions in China. In particular, point-wise mutual information is shown to be accurate in quantifying the strength of connections. We developed an interactive analyzing software framework for this study, and released the data and code online.
To address the issue of internal network security, Software-Defined Network(SDN) technology has been introduced to large-scale cloud centers because it not only improves network performance but also deals with network attacks. To prevent man-in-the-middle and denial of service attacks caused by an address resolution protocol bug in an SDN-based cloud center, this study proposed a Bayes-based algorithm to calculate the probability of a host being an attacker and further presented a detection model based on the algorithm. Experiments were conducted to validate this method.
In this paper, we study the skyline group problem over a data stream. An object can dominate another object if it is not worse than the other object on all attributes and is better than the other object on at least one attribute. If an object cannot be dominated by any other object, it is a skyline object. The skyline group problem involves finding k-item groups that cannot be dominated by any other k-item group. Existing algorithms designed to find skyline groups can only process static data. However, data changes as a stream with time in many applications,and algorithms should be designed to support skyline group queries on dynamic data. In this paper, we propose new algorithms to find skyline groups over a data stream. We use data structures, namely a hash table, dominance graph, and matrix, to store dominance information and update results incrementally. We conduct experiments on synthetic datasets to evaluate the performance of the proposed algorithms. The experimental results show that our algorithms can efficiently find skyline groups over a data stream.
In cloud computing applications, users’ data and applications are hosted by cloud providers. This paper proposed an access control scheme that uses a combination of discretionary access control and cryptographic techniques to secure users’ data and applications hosted by cloud providers. Many cloud applications require users to share their data and applications hosted by cloud providers. To facilitate resource sharing, the proposed scheme allows cloud users to delegate their access permissions to other users easily. Using the access control policies that guard the access to resources and the credentials submitted by users, a third party can infer information about the cloud users. The proposed scheme uses cryptographic techniques to obscure the access control policies and users’ credentials to ensure the privacy of the cloud users. Data encryption is used to guarantee the confidentiality of data. Compared with existing schemes, the proposed scheme is more flexible and easy to use. Experiments showed that the proposed scheme is also efficient.
Cloud monitoring is of a source of big data that are constantly produced from traces of infrastructures,platforms, and applications. Analysis of monitoring data delivers insights of the system’s workload and usage pattern and ensures workloads are operating at optimum levels. The analysis process involves data query and extraction, data analysis, and result visualization. Since the volume of monitoring data is big, these operations require a scalable and reliable architecture to extract, aggregate, and analyze data in an arbitrary range of granularity. Ultimately, the results of analysis become the knowledge of the system and should be shared and communicated. This paper presents our cloud service architecture that explores a search cluster for data indexing and query. We develop REST APIs that the data can be accessed by different analysis modules. This architecture enables extensions to integrate with software frameworks of both batch processing(such as Hadoop) and stream processing(such as Spark) of big data. The analysis results are structured in Semantic Media Wiki pages in the context of the monitoring data source and the analysis process. This cloud architecture is empirically assessed to evaluate its responsiveness when processing a large set of data records under node failures.
In recent years, Compressed Sensing(CS) has been a hot research topic. It has a wide range of applications, such as image processing and speech signal processing owing to its characteristic of removing redundant information by reducing the sampling rate. The disadvantage of CS is that the number of iterations in a greedy algorithm such as Orthogonal Matching Pursuit(OMP) is fixed, thus limiting reconstruction precision.Therefore, in this study, we present a novel Reducing Iteration Orthogonal Matching Pursuit(RIOMP) algorithm that calculates the correlation of the residual value and measurement matrix to reduce the number of iterations.The conditions for successful signal reconstruction are derived on the basis of detailed mathematical analyses.When compared with the OMP algorithm, the RIOMP algorithm has a smaller reconstruction error. Moreover, the proposed algorithm can accurately reconstruct signals in a shorter running time.
In this study, we present a framework based on a prediction model that facilitates user access to a number of services in a smart living environment. Users must be able to access all available services continuously equipped with mobile devices or smart objects without being impacted by technical constraints such as performance or memory issues, regardless of their physical location and mobility. To achieve this goal, we propose the use of cloudlet-based architecture that serves as distributed cloud resources with specific ranges of influence and a realtime processing framework that tracks events and preferences of the end consumers, predicts their requirements,and recommends services to optimize resource utilization and service response time.
Mobile devices are resource-limited, and task migration has become an important and attractive feature of mobile clouds. To validate task migration, we propose a novel approach to the simulation of task migration in a pervasive cloud environment. Our approach is based on Colored Petri Net(CPN). In this research, we expanded the semantics of a CPN and created two task migration models with different task migration policies: one that took account of context information and one that did not. We evaluated the two models using CPN-based simulation and analyzed their task migration accessibility, integrity during the migration process, reliability, and the stability of the pervasive cloud system after task migration. The energy consumption and costs of the two models were also investigated. Our results suggest that CPN with context sensing task migration can minimize energy consumption while preserving good overall performance.
Cloud computing has become a significant computing model in the IT industry. In this emerging model,computing resources such as software, hardware, networking, and storage can be accessed anywhere in the world on a pay-per-use basis. However, storing sensitive data on un-trusted servers is a challenging issue for this model. To guarantee confidentiality and proper access control of outsourced sensitive data, classical encryption techniques are used. However, such access control schemes are not feasible in cloud computing because of their lack of flexibility, scalability, and fine-grained access control. Instead, Attribute-Based Encryption(ABE) techniques are used in the cloud. This paper extensively surveys all ABE schemes and creates a comparison table for the key criteria for these schemes in cloud applications.
Smartphones and mobile tablets are rapidly becoming indispensable in daily life. Android has been the most popular mobile operating system since 2012. However, owing to the open nature of Android, countless malwares are hidden in a large number of benign apps in Android markets that seriously threaten Android security. Deep learning is a new area of machine learning research that has gained increasing attention in artificial intelligence. In this study, we propose to associate the features from the static analysis with features from dynamic analysis of Android apps and characterize malware using deep learning techniques. We implement an online deep-learning-based Android malware detection engine(Droid Detector) that can automatically detect whether an app is a malware or not. With thousands of Android apps, we thoroughly test Droid Detector and perform an indepth analysis on the features that deep learning essentially exploits to characterize malware. The results show that deep learning is suitable for characterizing Android malware and especially effective with the availability of more training data. Droid Detector can achieve 96.76% detection accuracy, which outperforms traditional machine learning techniques. An evaluation of ten popular anti-virus softwares demonstrates the urgency of advancing our capabilities in Android malware detection.