基于遗传算法和LSSVM的网络安全事件发生频率预测

Since the frequency of network security incidents is nonlinear, traditional prediction methods such as ARMA, Gray systems are difficult to deal with the problem. When the size of sample is small, methods based on artificial neural network may not reach a high degree of preciseness. Least Squares Support Vector Machines (LSSVM) is a kind of machine learning methods based on the statistics learning theory, it can be applied to solve small sample and non-linear problems very well. This paper applied LSSVM to predict the occur frequency of network security incidents. To improve the accuracy, it used an improved genetic algorithm to optimize the parameters of LSSVM. Verified by real data sets, the improved genetic algorithm (IGA) converges faster than the simple genetic algorithm (SGA), and has a higher efficiency in the optimization procedure. Specially, the optimized LSSVM model worked very well on the prediction of frequency of network security incidents.     

基于共生矩阵的电子商务交易日志异常检测

针对电子商务中用户交易行为合法与否的问题,提出了一种基于共生矩阵的异常检测算法.该算法利用共生矩阵对用户的交易行为建模,通过PCA方法建立共生矩阵空间,从而得到用户正常交易模式.在检测阶段,对待测数据产生的共生矩阵进行了修正并获取用户的交易模式,通过矩阵2-范数计算用户交易模式和其正常模式之间的距离并以此来判断用户的交易行为是否异常.实验表明,相比于其它的几种方法,本文的方法具有更高的检测性能.     

大型分布式系统部署一致性的研究与实现

随着网络应用向分布式方向的发展,系统的规模越来越大,随之而来的就是系统服务部署的一致性等问题。文章针对系统部署一致性,首先引入五种系统信息描述子,然后讨论了影响系统一致性的各种操作及对其处理方法,最后提出了一种基于一致性的对象传输策略。     

面向OLAP的高效海量数据存储技术研究与实现

文章在分析了OLAP大规模海量多维数据特点的基础上,针对当前一般规模关系数据库处理海量多维数据能力的不足,通过使用数据库分区技术和并行磁盘组技术,设计并实现了一种高效的、面向OLAP应用的数据存储管理结构。并针对传统查询优化器对于大规模海量数据统计信息更新不及时的问题,设计了一种基于分区技术的统计方法。实验证明,该设计可以对百TB级的多维海量文本数据进行有效的管理。     

基于多维熵序列分类的骨干网上流量异常检测

Detecting traffic anomalies is essential for diagnosing attacks. High-Speed Backbone Networks (HSBN) require Traffic Anomaly Detection Systems (TADS) which are accurate (high detection and low false positive rates) and efficient. The proposed approach utilizes entropy as traffic distributions metric over some traffic dimensions. An efficient algorithm, having low computational and space complexity, is used to estimate entropy. Entropy values over all dimensions are collected to form a detection vector for every sliding window. One class support vector machine classifies all detection vectors into one of two groups: abnormal vectors and normal vectors. A Multi-Windows Correlation Algorithm (MWCA) calculates comprehensive anomaly scores observed in a sequence of windows in order to reduce false positive rates and obtain high detection rates. Some real-world traffic traces have been used to validate and evaluate the efficiency and accuracy of this system through three experiments. In Experiment 1, the estimating algorithm of entropy which costs less memory and runs faster than traditional algorithms is more suitable for detection anomalies. In Experiment 2, the classification and correlation algorithms can improve the detection accuracy significantly. Experiment 3 compares the subject system and three well-known systems. Ours system is the most accurate one. Those results have indicated that the proposed system significantly improves the accuracy and efficiency.     

基于用户主题模型的微博用户兴趣挖掘(英文)

Microblogs have become an important platform for people to publish,transform information and acquire knowledge.This paper focuses on the problem of discovering user interest in microblogs.In this paper,we propose a topic mining model based on Latent Dirichlet Allocation(LDA) named user-topic model.For each user,the interests are divided into two parts by different ways to generate the microblogs:original interest and retweet interest.We represent a Gibbs sampling implementation for inference the parameters of our model,and discover not only user's original interest,but also retweet interest.Then we combine original interest and retweet interest to compute interest words for users.Experiments on a dataset of Sina microblogs demonstrate that our model is able to discover user interest effectively and outperforms existing topic models in this task.And we find that original interest and retweet interest are similar and the topics of interest contain user labels.The interest words discovered by our model reflect user labels,but range is much broader.     

基于Filter-ary-Sketch数据结构的骨干网异常检测研究

针对骨干网上异常检测的特殊要求,提出了一种基于Filter-ary-Sketch数据结构的异常检测方法。该方法通过Filter-ary-Sketch实时记录网络流量信息,然后每隔一定周期进行基于多维熵值的异常检测。如果出现异常则根据Filter-ary-Sketch记录的流量信息进行异常点定位,最后利用Bloom Filter中记录的源IP信息进行恶意流量阻断。该方法能够检测多种类型的网络攻击,且能有效地进行恶意流量阻断。利用实际骨干网流量数据,分别从效率和精度2个方法进行对比实验,取得了较好的效果。     

一种高效的OLAP最值查询算法

In the process of analyzing the large-scale network security situation, the data we faced are always flooded and messy, and the information is difficult to obtain with respond to the query timely. Online analytical processing which use the Data-cube as a data source directly, calculated all or part of the Data-cube in advance, and it can reduce the query response time significantly. This paper considers a class of queries,called the Partial-MAX/MIN query. We introduce Rank Decision Tree(RD-Tree) and it’s searching algorithm for efficient processing of the partial-max/min queries.Through experiments, we show our approach has an efficient processing capability for partial-max/min queries.     

基于电子身份的虚拟资产保全系统的研究与实现

随着电子信息技术的迅速普及和广泛应用,网络面临的安全问题也随之而来.本文从虚拟资产的安全问题出发,首先分析了目前虚拟资产存在的安全问题;然后对eID(electronic IDentity)技术进行了简要的阐述;最后对虚拟资产保全系统的安全对策进行了研究,提出了基于eID的虚拟资产保全在虚拟资产交易中的应用,提高了虚拟资产交易的安全性,规范网络虚拟资产领域体系结构,保障虚拟资产交易安全实施.基于eID的虚拟资产保全适合各种网络领域,电子商务、网络游戏等.基于eID的虚拟资产保全系统表明使用eID技术可以提高虚拟资产交易的安全性.     

分布式海量文本检索系统研究

文章利用分布式中间件技术和数据库技术实现海量数据高速加载与快速检索系统,针对数据库系统文本索引较慢等问题,采用并行索引方式来实现了一种可线性扩展的分布式海量文本数据检索系统。