检索结果-南通市图书馆

Malicious Traffic Detection in IoT and Local Networks Using Stacked Ensemble Classifier

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Computers, Materials & Continua 2022年第4期71卷 489-515页

作者： R.D.pubudu L.Indrasiri Ernesto Lee Vaibhav Rupapara Furqan Rustam Imran Ashraf School of Computing and Mathematics Charles Sturt UniversityAustralia Department of Computer Science Broward CollegeBroward CountyFloridaUSA School of Computing and Information Sciences Florida International UniversityUSA Department of Computer Science Khwaja Fareed University of Engineering and Information TechnologyRahim Yar KhanPakistan Department of Information and Communication Engineering Yeungnam UniversityGyeongsan-si38541Korea

Malicious traffic detection over the internet is one of the challenging areas for researchers to protect network infrastructures from any malicious *** shortcomings of a network system can be leveraged by an attacker to get unauthorized access through malicious *** from such attacks requires an efficient automatic system that can detect malicious traffic timely and avoid system ***,many automated systems can detect malicious activity,however,the efficacy and accuracy need further improvement to detect malicious traffic from multi-domain *** present study focuses on the detection of malicious traffic with high accuracy using machine learning *** proposed approach used two datasets UNSW-NB15 and IoTID20 which contain the data for IoT-based traffic and local network traffic,*** datasets were combined to increase the capability of the proposed approach in detecting malicious traffic from local and IoT networks,with high *** merging both datasets requires an equal number of features which was achieved by reducing feature count to 30 for each dataset by leveraging principal component analysis(PCA).The proposed model incorporates stacked ensemble model extra boosting forest(EBF)which is a combination of tree-based models such as extra tree classifier,gradient boosting classifier,and random forest using a stacked ensemble *** results show that EBF performed significantly better and achieved the highest accuracy score of 0.985 and 0.984 on the multi-domain dataset for two and four classes,respectively.

关键词： Stacked ensemble PCA malicious traffic detection classification machine learning

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

基于视频的智能零售柜关键算法研究

基于视频的智能零售柜关键算法研究

作者： pubudu Ekanayake 厦门大学

学位级别：硕士

智能零售店已经成为吸引许多科技公司的关注的活跃话题。亚马逊、深兰科技奥兰治和IBM等公司已经开始通过搭建完整的智能零售店或零售柜来提高客户的购物体验。这些公司正在使用较为复杂的集成系统来实现其目标。但是,在考虑具体搭建一... 详细信息

智能零售店已经成为吸引许多科技公司的关注的活跃话题。亚马逊、深兰科技奥兰治和IBM等公司已经开始通过搭建完整的智能零售店或零售柜来提高客户的购物体验。这些公司正在使用较为复杂的集成系统来实现其目标。但是,在考虑具体搭建一个小规模的智能零售店场景或零售柜时,首先需要解决一些关键问题:如何生成和标记属于某个域的所需图像数据集,比如,拟售商品在不同视角下的拍照图像;设计用于所售商品检测识别机器学习轻量化模型,它要同时满足精度、速度和存储容量等多个方面的要求;设计基于客户人脸图像的年龄估计和性别识别的轻量化机器学习模型。本文在较为全面地整理归纳智能零售店和零售柜的基础上,提出了一款智能零售柜总体设计方案,并就其中的三个关键问题,进行较为深入的研究,提出并实现了相应的解决方案。为了生成用于深度学习训练的带标注的图像数据集,本文设计了一条简单高效的人机协同的处理流水线。首先,对于每一类拟出售的商品,通过人工拍照或其它渠道,采集得到包含有该商品的图像,并赋予商品的类标属性,形成初步的图像数据集。随后,从每类商品中随机选择小部分图像,采用预训练的Mask RCNN模型,生成可疑目标的边界外框,经过人工验证,分拣出正确目标,并把硬误检目标和背景目标都归类为背景。据此分拣数据,采用VGG16提取特征,训练出一个目标分类器备用。然后,对于初始图像数据集中的每张图像,再次使用预训练的Mask RCNN提取可疑目标及其边框坐标,采用VGG16提取特征,使用上述中训练过的目标分类器,生成可疑目标的类标。最后,再经过人工审核确认,选出那些边框坐标和类标都正确的目标,组织成标准格式的带标注的图像数据集。该标注流水线可有效降低标注的人工成本和时间成本。使用轻量级深度学习模型对商品图像进行目标检测识别是本文的另一个重点工作。本文在采用基于CNN模型的单阶段目标检测算法处理流程的基础上,引入了一种自定义模块,它有助于减少CNN模型的参数数量,同时保持模型的原始精度。这种方法具有一定的通用性,通过在原始深度学习模型中进行一些小的更改,可以将设计的自定义模块插入到原始模型中。设计自定义模块的主要思想是通过减少模型参数的数量,从而降低保存模型权重的计算成本和存储容量,同时保持原始模型所保持的精度。本文设计的自定义模块在YOLO模型中将参数数量减少了 41.77%。本文设计了一个轻量级模型架构从客户图像中检测出人脸目标并估计出客户的年龄和性别。通过把原来相互独立的年龄估计模块和性别识别模块进行适当的更改,设计出一个能对年龄和性别同时进行估计的轻量级模型,降低了模型的容量和检测时间。年龄和性别的估计结果,将用于实现在未来版本中的产品推荐功能。本文的主要创新点是:（1）一种简单有效的图像数据库构建与边框标注的智能处理流水线及其核心算法;（2）引入自定义模块到目标检测的深度学习模型中,在保持原始模型精度的同时减少模型的参数数量。（3）构造了一个有效的轻量级CNN模型,用于从客户的面部图像中同时估计出客户的年龄和性别。

关键词：智能零售柜商品检测商品识别边框标注年龄估计性别估计

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

基于私有云的e-Learning架构研究

基于私有云的e-Learning架构研究

作者： JAYASENA,KUDAMADUWAGE pubudu NUWANTHIKA 武汉理工大学

学位级别：硕士

云计算为e-Learing提供了更好的平台。现在多数e-Learning平台不能在公有或私有云平台与私有网络架构之间共享资源,一般需要花费额外代价去部署环境。本文提出了一种基于VPN和私有云的e-Learning架构,能帮助学生在低成本的情况下,轻松... 详细信息

云计算为e-Learing提供了更好的平台。现在多数e-Learning平台不能在公有或私有云平台与私有网络架构之间共享资源,一般需要花费额外代价去部署环境。本文提出了一种基于VPN和私有云的e-Learning架构,能帮助学生在低成本的情况下,轻松建立和配置自己的在线学习环境,高效分享资源。本文主要工作分为如下三个方面:(1)提出基于私有云的e-Learning的整体架构该架构由私有云、在线学习、校园网络和VPN部分组成。通过开源软件实现私有云,并可在虚拟机上高效运行;e-Learning系统主要包括计算机科学课程虚拟机、备份系统以及管理用户账户的基于角色认证系统;并采用Eucalyptus结构和虚拟隧道完成交互功能。(2)利用VPN将校园网与私有云进行集成VPN为校园网和私有云之间的通信提供了专用网络。当有地址链接到VPN时,云管理员允许用户使用任意的IP地址去访问其中的资源而不用考虑冲突。虚拟私有云使用VPN来创建安全信道,消除了云计算和企业级组件中的复杂配置问题;把安全VPN链接扩展到了云架构虚拟机之中,e-Learning平台与其他位置的多平台之间的连接也变得可行和可扩展。说明了该架构能够允许本地网络与基于桉树(Eucalyptus)的带有VPN隧道的私有云之间的互通信。(3)所提出架构的实现给出了架构搭建所需的软硬件环境并做出了整体部署策略;通过呈现节点控制器,集群控制器以及云控制器的所有配置展示了私有云架构的建立,并描述了在私有云架构中,图像管理、实例、卷和快照的创建。其中:e-Learning平台实现了基于角色的认证系统,用户账户通过轻量级目录访问协议存储在中心数据库中;在私有云域以服务器模式运行Open VPN来实现VPN服务器,客户端以客户端模式运行Open VPN,连接到服务器,从私有云内网获得路由,然后通过VPN隧道在内网中访问服务器。

关键词：私有云在线学习虚拟私有网络资源共享虚拟化

Stochastic Modelling of Vulnerability Life Cycle and Security Risk Evaluation

同方学位论文库评论

在线全文

同方学位论文库

学校读者我要写书评

暂无评论

Journal of Information Security 2016年第4期7卷 269-279页

作者： Sasith M. Rajasooriya Chris P. Tsokos pubudu Kalpani Kaluarachchi Department of Mathematics and Statistics University of South Florida Tampa Florida USA

The objective of the present study is to propose a risk evaluation statistical model for a given vulnerability by examining the Vulnerability Life Cycle and the CVSS score. Having a better understanding of the behavior of vulnerability with respect to time will give us a great advantage. Such understanding will help us to avoid exploitations and introduce patches for a particular vulnerability before the attacker takes the advantage. Utilizing the proposed model one can identify the risk factor of a specific vulnerability being exploited as a function of time. Measuring of the risk factor of a given vulnerability will also help to improve the security level of software and to make appropriate decisions to patch the vulnerability before an exploitation takes place.

关键词： Stochastic Modelling Security Risk Evaluation Vulnerability Life Cycle Risk Factor

Cybersecurity: A Statistical Predictive Model for the Expected Path Length

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Information Security 2016年第3期7卷 112-128页

作者： pubudu Kalpani Kaluarachchi Chris P. Tsokos Sasith M. Rajasooriya Department of Mathematics and Statistics University Of South Florida Tampa FL USA

The object of this study is to propose a statistical model for predicting the Expected Path Length (expected number of steps the attacker will take, starting from the initial state to compromise the security goal—EPL) in a cyber-attack. The model we developed is based on utilizing vulnerability information along with having host centric attack graph. Utilizing the developed model, one can identify the interaction among the vulnerabilities and individual variables (risk factors) that drive the Expected Path Length. Gaining a better understanding of the relationship between vulnerabilities and their interactions can provide security administrators a better view and an understanding of their security status. In addition, we have also ranked the attributable variables and their contribution in estimating the subject length. Thus, one can utilize the ranking process to take precautions and actions to minimize Expected Path Length.

关键词： Vulnerability Attack Graph Markov Model Security Evaluation Expected Path Length CVSS

Nonhomogeneous Risk Rank Analysis Method for Security Network System

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

International Journal of Communications, Network and System Sciences 2019年第1期12卷 1-10页

作者： pubudu Kalpani Hitigala Kaluarachchilage Chris P. Tsokos Sasith M. Rajasooriya Department of Mathematical and Physical Sciences Miami University Middletown OH USA Department of Mathematics and Statistics University of South Florida Tampa FL USA Department of Mathematics University of Dayton Dayton OH USA

Security measures for a computer network system can be enhanced with better understanding the vulnerabilities and their behavior over the time. It is observed that the effects of vulnerabilities vary with the time over their life cycle. In the present study, we have presented a new methodology to assess the magnitude of the risk of a vulnerability as a “Risk Rank”. To derive this new methodology well known Markovian approach with a transition probability matrix is used including relevant risk factors for discovered and recorded vulnerabilities. However, in addition to observing the risk factor for each vulnerability individually we have introduced the concept of ranking vulnerabilities at a particular time taking a similar approach to Google Page Rank Algorithm. New methodology is exemplified using a simple model of computer network with three recorded vulnerabilities with their CVSS scores.

关键词： Markov Chain Vulnerability Non Homogeneous Risk Analysis Network Security Google Page Rank

Non-Homogeneous Stochastic Model for Cyber Security Predictions

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Information Security 2018年第1期9卷 12-24页

作者： pubudu Kalpani Kaluarachchi Chris P. Tsokos Sasith M. Rajasooriya Department of Mathematical and Physical Sciences Miami University Middletown Ohio USA Distinguished University Professor Department of Mathematics and Statistics University of South Florida Tampa Florida USA Department of Statistics Miami University Oxford Ohio USA

Any computer system with known vulnerabilities can be presented using attack graphs. An attacker generally has a mission to reach a goal state that he expects to achieve. Expected Path Length (EPL) [1] in the context of an attack graph describes the length or number of steps that the attacker has to take in achieving the goal state. However, EPL varies and it is based on the “state of vulnerabilities” [2] [3] in a given computer system. Any vulnerability throughout its life cycle passes through several stages that we identify as “states of the vulnerability life cycle” [2] [3]. In our previous studies we have developed mathematical models using Markovian theory to estimate the probability of a given vulnerability being in a particular state of its life cycle. There, we have considered a typical model of a computer network system with two computers subject to three vulnerabilities, and developed a method driven by an algorithm to estimate the EPL of this network system as a function of time. This approach is important because it allows us to monitor a computer system during the process of being exploited. Proposed non-homogeneous model in this study estimates the behavior of the EPL as a function of time and therefore act as an index of the risk associated with the network system getting exploited.

关键词： Vulnerability Attack Graph Markov Model Security Evaluation Expected Path Length (EPL) Common Vulnerability Scoring System (CVSS) Non Homogeneous Stochastic Model

Cyber Security: Nonlinear Stochastic Models for Predicting the Exploitability

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Information Security 2017年第2期8卷 125-140页

作者： Sasith M. Rajasooriya Chris. P. Tsokos pubudu Kalpani Kaluarachchi Department of Mathematics and Statistics University Of South Florida Tampa Florida USA

Obtaining complete information regarding discovered vulnerabilities looks extremely difficult. Yet, developing statistical models requires a great deal of such complete information about the vulnerabilities. In our previous studies, we introduced a new concept of “Risk Factor” of vulnerability which was calculated as a function of time. We introduced the use of Markovian approach to estimate the probability of a particular vulnerability being at a particular “state” of the vulnerability life cycle. In this study, we further develop our models, use available data sources in a probabilistic foundation to enhance the reliability and also introduce some useful new modeling strategies for vulnerability risk estimation. Finally, we present a new set of Non-Linear Statistical Models that can be used in estimating the probability of being exploited as a function of time. Our study is based on the typical security system and vulnerability data that are available. However, our methodology and system structure can be applied to a specific security system by any software engineer and using their own vulnerabilities to obtain their probability of being exploited as a function of time. This information is very important to a company’s security system in its strategic plan to monitor and improve its process for not being exploited.

关键词： Vulnerability Lifecycle Stochastic Modeling Security Risk Factor Markov Process Risk Evaluation

Modeling the Flow Regime Near the Source in Underwater Gas Releases

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Journal of Marine Science and Application 2016年第4期15卷 433-441页

作者： Lakshitha T. Premathilake Poojitha D. Yapa Indrajith D. Nissanka pubudu Kumarage Department of Civil and Environmental Engineering Clarkson University Potsdam NY 13699 USA

Recent progress in calculating gas bubble sizes in a plume, based on phenomenological approaches using the release conditions is a significant improvement to make the gas plume models self-reliant. Such calculations require details of conditions Near the Source of Plume （NSP）; （i.e. the plume/jet velocity and radius near the source）, which inspired the present work. Determining NSP conditions for gas plumes are far more complex than that for oil plumes due to the substantial density difference between gas and water. To calculate NSP conditions, modeling the early stage of the plume is important. A novel method of modeling the early stage of an underwater gas release is presented here. Major impact of the present work is to define the correct NSP conditions for underwater gas releases, which is not possible with available methods as those techniques are not based on the physics of flow region near the source of the plume/jet. We introduce super Gaussian profiles to model the density and velocity variations of the early stages of plume, coupled with the laws of fluid mechanics to define profile parameters. This new approach, models the velocity profile variation from near uniform, across the section at the release point to Gaussian some distance away. The comparisons show that experimental data agrees well with the computations.

关键词： underwater gas releases bubble plumes near source conditions plumes/jets oil and gas spill models