Intrusion detection is an essential task in the cyber threat environment. Machine learning and deep learning techniques have been applied for intrusion detection. However, most of the existing research focuses on the model work but ignores the fact that poor data quality has a direct impact on the performance of a machine learning system. More attention should be paid to the data work when building a machine learning-based intrusion detection system. This article first summarizes existing machine learning-based intrusion detection systems and the datasets used for building these systems. Then the data preparation workflow and quality requirements for intrusion detection are discussed. To figure out how data and models affect machine learning performance, we conducted experiments on 11 HIDS datasets using seven machine learning models and three deep learning models. The experimental results show that BERT and GPT were the best algorithms for HIDS on all of the datasets. However, the performance on different datasets varies, indicating the differences between the data quality of these datasets. We then evaluate the data quality of the 11 datasets based on quality dimensions proposed in this paper to determine the best characteristics that a HIDS dataset should possess in order to yield the best possible result. This research initiates a data quality perspective for researchers and practitioners to improve the performance of machine learning-based intrusion detection.
Service convergence, content digitization, rapid and flexible service delivery, reduction of capital and operating costs, economies of scale, changes in telecom policy and regulation, and ever increasing competition have been key factors in the evolution of virtualized Next Generation Networks (vNGN). IPcentric converged networks aim to provide a multitude of services over a single network infrastructure. Tremendous success and benefit of server virtualization in data centers is driving the adaption of network virtualization. Network virtualization is applicable to enterprise data center, and enterprise as well as wide area networks. The focus of this paper is network virtualization aspects of service providers’ next generation network. The key factors for moving to virtualized network is optimal use and sharing of network infrastructure even among competitive service providers, programmability of network and rapid
Internet of Things (IoT) refers to heterogeneous systems and devices (often referred to as smart objects) that connect to the internet, and is an emerging and active area of research with tremendous technological, social, and economical value for a hyper-connected world.In this paper, we will discuss how billions of these internet connected devices and machines will change the future in which we shall live, communicate and do the business.The devices, which would be connected to the internet, could vary from simple systems on chip (SOC) without any Operating System (OS) to highly powerful processor with intelligent OS with widely varying processing capability and diverse protocol support.Many of these devices can also communicate with each other directly in a dynamic manner.A key challenge is: how to manage such a diverse set of devices of such massive scale in a secured and effective manner without breaching privacy.In this paper, we will discuss various management issues and challenges related to different communication protocol support and models, device management, security, privacy, scalability, availability and analytic support, etc., in managing IoT.The key contribution of this paper is proposal of a reference management system architecture based on cloud technology in addressing various issues related to management of IoThaving billions of smart objects.
Service convergence, content digitization, rapid and flexible service delivery, reduction of capital and operating costs, economies of scale, changes in telecom policy and regulation, and ever increasing competition have been key factors in the evolution of virtualized Next Generation Networks (vNGN).IPcentric converged networks aim to provide a multitude of services over a single network infrastructure.Tremendous success and benefit of server virtualization in data centers is driving the adaption of network virtualization.Network virtualization is applicable to enterprise data center, and enterprise as well as wide area networks.The focus of this paper is network virtualization aspects of service providers' next generation network.The key factors for moving to virtualized network is optimal use and sharing of network infrastructure even among competitive service providers, programmability of network and rapid introduction of new service and standard based on open platform rather than proprietary implementation.Evolving Software Defined Network (SDN) and Network Function Virtualization (NFV) shall enable common network infrastructure sharing, control, and management at a higher layer thus making network devices more generic and less intelligent, thus enabling cost competitiveness and quick service delivery.Network virtualization shall enable key benefits such as lower cost, flexibility, efficiency, and security, However, the deployment of virtualized next generation networks has brought its unique challenges for network managers and planners, as the network has to be planned in a comprehensive way with effective management of virtual network elements, its correlation with physical infrastructure and monitoring of control functions and server platforms.This paper discusses generic next generation network, its virtualization, and addresses the challenges related to the planning and managing of virtualized next generation networks.This paper proposes a reference OSS model enabling effective management of vNGN, which is key contribution of this paper.
The scope and purpose of application comprehension is much broader than that of program comprehension. Application comprehension can be viewed as a spectrum spanning the gamut comprising code-level understanding at one end (low level) and understanding the architecture of interorganizational systems at the other end (high level). The nature and the depth of knowledge sought through application comprehension is directly related to the purpose at hand. In this paper, we propose a unified conceptual framework for application comprehension. The framework is influenced by Bloom's taxonomy. The proposed framework considers several aspects of application comprehension and draws upon our experience in developing large-scale, multi-tier distributed applications for brokerage and financial services. We discuss how the proposed conceptual framework can be implemented by leveraging the sophisticated tools that are available as open-source software. We conclude the paper by indicating how the proposed framework can be used to learn software engineering principles, tools, and practices in education and training contexts.
In the present world, it is difficult to realize any computing application working on a standalone computing device without connecting it to the network.A large amount of data is transferred over the network from one device to another.As networking is expanding, security is becoming a major concern.Therefore, it has become important to maintain a high level of security to ensure that a safe and secure connection is established among the devices.An intrusion detection system (IDS) is therefore used to differentiate between the legitimate and illegitimate activities on the system.There are different techniques are used for detecting intrusions in the intrusion detection system.This paper presents the different clustering techniques that have been implemented by different researchers in their relevant articles.This survey was carried out on 30 papers and it presents what different datasets were used by different researchers and what evaluation metrics were used to evaluate the performance of IDS.This paper also highlights the pros and cons of each clustering technique used for IDS, which can be used as a basis for future work.
This paper discusses a retrieval scheme for an information retrieval system in which the feedback from a number of users of the system about its performance (global feedback) is stored in the form of clusters called user-oriented clusters. The clusters are described by using the description of its constituent documents. The clusters and queries are represented as vectors and the measure of similarity between them is represented as the cosine of the angle between the two. The clusters are retrieved as per decreasing order of similarity with respect to a query. An important problem that arises in the context of cluster description is the significance of an index term assigned to documents. This problem, called term refinement problem, is formulated and solved. The experimental results of the proposed retrieval scheme are compared with those of the vector space model and the results obtained are encouraging.
