Study of Immune-Based Intrusion Detection Technology in Virtual Machines for Cloud Computing Environment

Gil

2020

Int J Communication

Summary In 5G networks, mobile network and service functions run as software on general‐purpose servers that are distributed across remote sites. Dedicated networks, such as Internet of Things (IoT) network, disaster network, and immersive media network, are virtualized as software solutions on common hardware equipment. This means a new network can be easily provisioned by modifying the configurations of the network based on software‐defined networking (SDN) and network functions virtualization (NFV). Furthermore, the 5G core network architecture toward flat architecture with distributed cloud is a key solution for providing service flexibility and scalability in order to handle an explosive increase in mobile data traffic. To create heterogeneous networks and services on 5G networks, we propose a location‐aware network virtualization method that aims at minimizing the network load and resource cost by appropriately selecting the relevant cloud (including Virtual Machines (VMs), virtual network function [VNF] nodes, applications, and resources) and mobile core entities to provide the required virtual networking services that facilitate secure isolation of the virtual networks with automated resource convergence. In addition, we propose a selective mobility management scheme for service continuity in cases of user equipment (UE) handover. The numerical results show the trade‐off between the different cost factors, ie, network cost and service resources cost in terms of the number of deployed clouds on 5G core networks.

Section: Background and Related Workmentioning

confidence: 99%

A location‐aware network virtualization and reconfiguration for 5G core network based on SDN and NFV

Gil

2020

Int J Communication

“…Yang started from the main idea of changes leading to danger,and established an adaptive danger signal extraction model based on finding changes [9]. Zhang presented an immune-inspired intrusion detection model in virtual machines of cloud computing environment, denoted IVMIDS, to ensure the safety of user-level applications in client virtual machines [10]. Rimiru described an integrated innate and adaptive immune system architecture which is shown to incorporate many properties of natural immune systems [11].Seresht proposed an agent-based approach using artificial immune system paradigms as a successful mechanism for a distributed intrusion detection system [12].…”

Section: Introductionmentioning

confidence: 99%

An Intrusion Detection Model Based On Danger Theory for Wireless Sensor Networks

Sun²,

Wang

2018

Int. J. Onl. Eng.

<strong>This paper, due to the intrusion detection problem in Wireless Sensor Networks, proposes an intrusion detection model based on the Danger Theory instead of the traditional Self-NonSelf theory. The intrusion detection model has two layers structure including danger perception and control decision, and it uses a multi-node cooperation mechanism. The perception node can realize the danger perception with Projection Pursuit Algorithm, and the decision node can detect the intrusion in detail with Extreme Learning Machine Algorithm. The logic process between their layers is consistent with the Danger Theory. The proposed model can realize the data trust between nodes with the Beta distribution trust evaluation method. By the simulations in the MATLAB, the proposed intrusion detection model on the whole is better than the SNS model at the aspects including classification training, danger perception, false negative rate, false positive rate and energy consumption.</strong>

Trans Emerging Tel Tech

An intelligent collaborative inference approach of service partitioning and task offloading for deep learning based service in mobile edge computing networks

Qin

Zhou

et al. 2021

As the rapid evolution of smart devices and real‐time applications, many new kinds of computation‐intensive services have been emerged successively and the corresponding requirements have been growing dramatically. Extended from cloud computing, mobile edge computing (MEC) is a novel technology which can provide powerful computing resource at the proximity of resource‐restrained mobile devices. Thus, it enables collaboration between edge server and mobile device, which can improve the quality of experience for users. In this article, we propose an intelligent collaborative inference (ICI) approach for real‐time computation‐intensive services in MEC network, which can achieve intelligent service partitioning and partial task offloading. Since machine learning algorithms have been applied in many applications with the advancement of big data and computing power, we focus on the services based on deep‐learning. Particularly, we research a service based on Pose‐Net model to achieve human pose estimation in the field of computer vision. And we design relevant ICI algorithm to achieve fine‐grained video stream processing in consideration of video service requirement, deep neural network (DNN) model structure, mobile device capability, wireless network condition, and cooperative server workload. Based on Python programming language and TensorFlow library, we test the ICI approach with some practical simulation parameters on real hardware platforms. The experiment results show that the presented ICI approach have superior performance in terms of service frame rate and client energy consumption than other benchmark approaches.