大数据场景下基于机器学习的5G云网告警关联分析

提出一种基于关联规则挖掘算法的5G云网告警分析方案,对机器学习算法FP-Growth进行契合5G云网告警场景的改进和应用,利用现网告警数据展开告警关联分析工作,挖掘网元及云侧告警之间的关联关系,并进行告警压缩和收敛,为5G云网故障分析和定位提供有效帮助。此外,基于实际告警数据对Apriori和FP-Growth算法的性能进行了比较,结果表明,FP-Growth关联规则挖掘算法与Apriori相比效率更高,更适合海量数据场景下的告警关联分析。     

基于改进贝叶斯正则化BP神经网络模型的网络安全态势预测方法研究

随着互联网的迅速发展,网络安全问题越来越严重,分析及预测网络安网络安全态势,对于网络安全具有重要意义。本文在网络安全态势量化的的基础上,改进贝叶斯算法,提出一种改进型贝叶斯正则化BP神经网络模型的网络安全态势预测方法,通过模拟网络环境进行数据分析,验证了该预测方法可以减小了训练误差和预测误差,提高了对网络安全态势预测精度,证明了该方法的可行性。     

SVM-PSO在网络安全态势预测中的应用研究

在网络安全态势预测中,使用支持向量机(SVM)与改进的粒子群优化算法(PSO)相结合的网络安全态势预测方法,不仅克服了PSO-SVM存在局部最优解及粒子早熟的问题,而且充分发挥了SVM收敛速度快、样本小、泛化能力强、机器学习的优点,提高了网络安全态势的预测精度。使得网络管理者能更好利用可视化的网络安全预测系统,对发现的网络安全弱点、预测到的威胁,及时采用相应的防范措施,从而实现对网络安全威胁及网络攻击实时、主动的防御。     

基于ADMPDE-WNN的网络安全态势预测方法

精确预测网络安全态势,对分析网络安全态势和趋势、调整安全策略具有重要意义。针对复杂网络系统规模变化,建立了层次化网络安全态势评估模型;在分析小波神经网络(WNN)基本原理及优缺点的基础上,将具有寻优能力强、收敛速度快的自适应局部增强微分进化算法(ADMPDE)与WNN算法相结合,提出了基于ADMPDE-WNN的态势预测方法。通过仿真实验分析,ADMPDE-WNN算法大大减小了训练误差和预测误差,提高了网络安全态势预测精度。基于ADMPDE-WNN的网络安全态势预测是一种科学、合理的预测方法,具有一定的理论意义和应用价值。     

基于云计算环境的数据挖掘算法研究

本文将介绍K-means算法的一般执行流程、云环境下K-means算法的实现、以及云环境下K-means算法的改进方法,还将从云计算环境下的数据挖掘算法、数据存储和管理技术、数据预处理技术、分类、聚类、关联规则挖掘和时序数据挖掘算法等方面进行探讨。     

基于多源数据融合的网络安全态势评估方法研究

针对层次分析法进行网络安全态势评估存在主观性过强的问题,文中提出了一种基于Hadoop的网络安全态势评估算法。该算法采用Hadoop作为并行数据融合平台,使用LSTM作为多数据特征提取算法。为了弥补分类功能的缺陷,通过随机森林模型增强算法的分类性能,最后将LSTM随机森林算法部署在Hadoop集群中,完成多源数据的融合。实验结果表明,相较于其他算法,所提算法的预测性能更强、误差更小,从而进一步提升了网络安全态势评估的精度。     

云计算环境下的网络安全估计模型态势仿真

在云计算环境下,传统方法采用终端网络监测方法进行网络安全估计,由于网络通信信道终端功率衰减性强,导致安全态势估计精度不高,检测性能不好。提出一种基于自适应数据分类和病毒感染隶属度特征提取的云计算环境下网络安全估计及态势预测算法。构建云计算环境下的网络安全估计模型,采用自适应数据分类算法对网络攻击信息数据进行聚类评估,提取网络攻击病毒数据的感染隶属度特征,实现网络安全态势预测和病毒攻击检测。仿真实验表明,该算法对病毒数据流预测精度较高,实现不同场景下的网络病毒流预测和数据检测,提高了云计算环境下网络抵御病毒攻击的能力。     

基于Spark的精准关联规则挖掘算法实现

为在大数据环境中精确地进行关联规则挖掘,基于分布式框架Spark,改进关联规则挖掘算法Apriori,解决使用该算法处理大规模数据时遇到的单机内存资源限制和性能缺陷,同时保证结果准确度。利用开源数据集和海量轨迹数据集评估算法的有效性,实验结果表明:与传统方法相比,改进后的Apriori算法进行规则挖掘能够得到相同准确度的结果,并且通过增加处理节点的数量灵活扩展待挖掘数据规模,从而使关联规则挖掘不再受数据规模限制。     

一种基于RF-SVM网络安全态势感知算法的应用研究

随着网络用户规模的大幅度增加,网络用户使用计算机的水平参差不齐,导致网络安全事故频频发生,提升网络安全态势感知已经成为研究的重点。本文提出了一种基于RF-SVM的网络安全态势感知算法,该算法引入回归思想,在网络入侵感知过程,充分地参考历史网络攻击数据,预测未来网络数据流中潜在的威胁,实验证明该算法能够有效地提升网络安全感知的准确度,降低预测误差。     

基于改进关联规则的危险Web信息挖掘技术研究

在Web网络中承载着不同的协议和网络信道,由此产生危险信息,给网络信息空间带来安全威胁,通过对危险Web信息的准确挖掘,可净化网络空间,确保网络安全。传统方法采用模糊关联规则算法进行危险Web信息分类挖掘,在干扰背景下,模糊聚类过容易受到干扰,导致很难建立有效的关联规则,挖掘效率较低。提出一种基于改进关联规则的危险Web信息挖掘技术。在建立关联规则前,引入Takens定理进行危险Web信息数据的相空间重构,构建Web网络的危险信息挖掘的信道模型,并对危险Web信息的信息流多源进程进行分类设计。设计自适应IIR级联滤波算法进行数据干扰滤波,运用以上方法对规则关联过程进行改进,实现危险Web信息的准确挖掘。仿真实验进行了性能验证,结果表明,采用该算法进行危险Web数据挖掘,去干扰性能较好,精度较高。     

Cloud security situation prediction method based on grey wolfoptimization and BP neural network

Aiming at the accuracy and error correction of cloud security situation prediction, a cloud security situation prediction method based on grey wolf optimization (GWO) and back propagation (BP) neural network is proposed.Firstly, the adaptive disturbance convergence factor is used to improve the GWO algorithm, so as to improve theconvergence speed and accuracy of the algorithm. The Chebyshev chaotic mapping is introduced into the positionupdate formula of GWO algorithm, which is used to select the features of the cloud security situation prediction dataand optimize the parameters of the BP neural network prediction model to minimize the prediction output error.Then, the initial weights and thresholds of BP neural network are modified by the improved GWO algorithm toincrease the learning efficiency and accuracy of BP neural network. Finally, the real data sets of Tencent cloudplatform are predicted. The simulation results show that the proposed method has lower mean square error (MSE)and mean absolute error (MAE) compared with BP neural network, BP neural network based on genetic algorithm(GA-BP), BP neural network based on particle swarm optimization (PSO-BP) and BP neural network based onGWO algorithm (GWO-BP). The proposed method has better stability, robustness and prediction accuracy.     

Internet of things intrusion detection model and algorithm based on cloud computing and multi-feature extraction extreme learning machine

With the rapid development of the Internet of Things (IoT), there are several challenges pertaining to security in IoT applications. Compared with the characteristics of the traditional Internet, the IoT has many problems, such as large assets, complex and diverse structures, and lack of computing resources. Traditional network intrusion detection systems cannot meet the security needs of IoT applications. In view of this situation, this study applies cloud computing and machine learning to the intrusion detection system of IoT to improve detection performance. Usually, traditional intrusion detection algorithms require considerable time for training, and these intrusion detection algorithms are not suitable for cloud computing due to the limited computing power and storage capacity of cloud nodes; therefore, it is necessary to study intrusion detection algorithms with low weights, short training time, and high detection accuracy for deployment and application on cloud nodes. An appropriate classification algorithm is a primary factor for deploying cloud computing intrusion prevention systems and a prerequisite for the system to respond to intrusion and reduce intrusion threats. This paper discusses the problems related to IoT intrusion prevention in cloud computing environments. Based on the analysis of cloud computing security threats, this study extensively explores IoT intrusion detection, cloud node monitoring, and intrusion response in cloud computing environments by using cloud computing, an improved extreme learning machine, and other methods. We use the Multi-Feature Extraction Extreme Learning Machine (MFE-ELM) algorithm for cloud computing, which adds a multi-feature extraction process to cloud servers, and use the deployed MFE-ELM algorithm on cloud nodes to detect and discover network intrusions to cloud nodes. In our simulation experiments, a classical dataset for intrusion detection is selected as a test, and test steps such as data preprocessing, feature engineering, model training, and result analysis are performed. The experimental results show that the proposed algorithm can effectively detect and identify most network data packets with good model performance and achieve efficient intrusion detection for heterogeneous data of the IoT from cloud nodes. Furthermore, it can enable the cloud server to discover nodes with serious security threats in the cloud cluster in real time, so that further security protection measures can be taken to obtain the optimal intrusion response strategy for the cloud cluster.     

蝙蝠算法优化RVM的校园网络安全研究

传统的应对网络威胁的手段是根据所发生的攻击针对性的提供补救措施,但是这种方式具有较强的滞后性,已难以满足现在快节奏的网络运行环境。如何提供一种对网络安全状况的量化指标,根据对网络安全的走势进行预测已经成为了如今的研究热点。文中针对网络安全的量化评估与预测问题,首先,提出了一种基于层次化评估模型的方法,实现了对网络安全态势的量化手段,将其从定性分析上升到了定量分析;其次,提出了一种基于相关向量机的网络安全态势预测模型,并通过蝙蝠算法提升了该模型的运行效率;最后,通过数据集的样本学习,验证了预测方法的有效性,该方法具有较高的精度和可靠性。     

银行交易网络的链路预测

基于银行交易具有动态变化、时效性和重复性的特点,文中通过对银行网络进行清洗和压缩,研究银行网络的基本拓扑统计性质和聚类结构,并得到交易网络满足复杂网络的小世界和无标度特性。针对已有的链路预测算法在动态网络预测中的不足,提出一种自适应的动态链路算法对银行客户交易进行预测。该方法在预测网络的基础上添加了节点重要性与节点连接强弱性两个特性,并将3种预测算法结合随机算法进行了对比分析。随后将这3种算法运用到具有动态交易特性的3类真实数据集中进行实验验证。实验结果显示,新算法的预测精度约为75%。将该算法与经典的预测算法进行比较发现,提出的算法在预测方面的性能提升了5%~10%。     

Cloud Dynamic Scheduling for Multimedia Data Encryption Using Tabu Search Algorithm

The cloud computing is interlinked with recent and out-dated technology. The cloud data storage industry is earning billion and millions of money through this technology. The cloud remote server storage is on-demand technology. The cloud users are expecting higher quality in minimal cost. The quality of service is playing a vital role in any latest technology. The cloud user always depends on thirty party service providers. This service provider is facing higher competition. The customer is choosing a service based on two parameters one is security and another one is cost. The reason behind this is all our personal data is stored on some third party server. The customer is expecting higher security level. The service provider is choosing many techniques for data security, best one is encryption mechanism. This encryption method is having many algorithms. Then again one problem is raised, that is which algorithm is best for encryption. The prediction of algorithm is one of major task. Each and every algorithm is having unique advantage. The algorithm performance is varying depends on file type. The proposed method of this article is to solve this encryption algorithm selection problem by using tabu search concept. The proposed method is to ensure best encryption method to reducing the average encode and decode time in multimedia data. The local search scheduling concept is to schedule the encryption algorithm and store that data in local memory table. The quality of service is improved by using proposed scheduling technique.

     

Network security situation automatic prediction model based on accumulative CMA-ES optimization

To improve the accuracy of the network security situation, a security situation automatic prediction model based on accumulative data preprocess and support vector machine (SVM) optimized by covariance matrix adaptive evolutionary strategy (CMA-ES) is proposed. The proposed model adopts SVM which has strong nonlinear ability. Also, the hyper parameters for SVM are optimized through the CMA-ES which owns good performance in finding optimization automatically. Considering the irregularity of network security situation values, we accumulate the original sequence, so that the internal rules of discrete data can be revealed and it is easy to model. Simulation experiments show that the proposed model has faster convergence-speed and higher prediction accuracy than other extant prediction models.     

自动计算重叠度的多源点云配准方法

针对多源点云配准存在噪声、部分重叠、不同模型的配准参数难确定等问题,提出一种基于贡献因子的改进TrICP算法。首先,使用改进体素降采样以及随机降采样对点云进行降采样。然后,利用改进算法的贡献因子来保留对配准贡献度更大的点对,使用奇异值分解法（SVD）对变换矩阵求解,同时计算距离曲线上的点经过原点的斜率来自动计算重叠度,实现点云的全自动配准。使用斯坦福大学的Bunny点云以及“茂县624”滑坡现场点云数据对改进算法及TrICP等多个算法进行对比实验。结果表明:相对于TrICP,改进算法在Bunny点云以及滑坡体点云上,配准速度分别提升50%和67%,且精度更高,并在添加大量噪声情况下仍能正确配准,这表明该算法能对含大量噪声、部分重叠、非同源的激光与影像重建点云进行可靠高效的自动配准,实现多源数据优势互补以获取目标的精准点云信息。     

基于大数据的安全态势感知系统研究

近年来,大数据、云计算等技术加速发展。同时,在信息安全威胁不断扩大和攻击手段日益复杂的影响下,工控网络安全形势呈严峻趋势。相比常规网络安全措施,网络安全态势感知能在一定程度上使工控网络安全现状有所改变。该感知系统可及时发现网络安全预测及监视等多个环节中存在的漏洞,能够正确评估现有的网络现状,并对网络可能带来的负面影响加以评估,将未来特定时段内的网络状况加以预测。网络,是大数据时代的必然产物,受网络技术的虚拟性影响,不可避免存在安全问题。基于此,文中在研究中首先分析了网络安全态势感知及技术。其次,总结了网络安全态势感知系统研究的框架。最后,研究了基于大数据的安全态势感知系统研究模块及实现。     

计算机病毒发展态势预测算法的评估

对计算机病毒发展态势预测,能够提前对网络安全状况进行判断,有利于做好事前防范,并建立预警机制。目前对计算机病毒发展态势的预测还处于探索阶段,传统算法在此方面的预测效果也尚不明确。这里比较了多种预测算法,如移动平均、态势预测、季节变动预测及线性回归等方法在实际计算机病毒发展分析上的预测准确率。通过对不同时间跨度,不同类型计算机病毒数据进行深入分析发现,线性回归和季节变动算法能够较好地适应具有时间周期性的计算机病毒日志数据。     

基于云计算的海量网络流量数据分析处理及关键算法研究

为了应对日益增长的网络流量数据量和对网络安全的需求,提高网络流量数据的处理效率和准确性,文中从云计算架构出发,设计并搭建了一个能承载大规模网络流量数据处理的云计算平台。基于该平台,采用了分布式存储、并行计算和机器学习等技术,对海量网络流量数据的预处理、聚类分析、异常检测等关键环节进行了研究。结果表明,基于云计算的海量网络流量数据分析处理的关键算法取得了显著成果。通过分布式存储和并行计算技术,实现了对海量网络流量数据的高效读写和处理。在预处理阶段,针对流量数据进行采样和滤波,减少了数据量,并保留了关键特征。在聚类分析方面,利用机器学习算法实现了对网络流量的分类和统计,通过构建模型、训练和优化算法,实现了对网络攻击和异常行为的准确识别和及时报警。