Innovative Defense Technologies in 5G and beyond Mobile Networks Using Machine Learning

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Networks".

Deadline for manuscript submissions: closed (31 March 2023) | Viewed by 10836

Special Issue Editors


E-Mail Website
Guest Editor
School of Software, Jiangxi Normal University, Nanchang 330022, China
Interests: trusted and trustworthy computing; multimedia communications; next-generation Internet technologies
Special Issues, Collections and Topics in MDPI journals

E-Mail Website
Guest Editor
Institute for Science and Engineering, Waseda University, Tokyo 169-8050, Japan
Interests: video streaming; AI/machine learning inspired wireless networks
Department of Computer Science, University of York, York YO10 5GH, UK
Interests: real-time systems; machine learning; data security

Special Issue Information

Dear Colleagues,

Emerging as the central building block of future networks, 5G and beyond mobile networks have shown the potential to support billions of mobile devices. Their boom, however, comes with the risk of being more susceptible to security threats, also imposing security challenges to networking technologies such as software-defined networking (SDN), network function virtualization (NFV), the Internet of Things (IoT) and mobile edge computing (MEC). Traditional security techniques may be insufficient, as they have the potential to fail to meet requirements such as ultra-low latency and deterministic properties. In addition, they may no longer be applicable, as cyberattacks have evolved with 5G and beyond networks, prompting unprecedented security risks.

Currently, machine learning (ML) technology is used in both industry and academia due to its data-driven feature for realizing high-performance networks. ML algorithms can be applied throughout networks to predict potential problems without the need of any external resources, making it a promising technique in detecting attacks in 5G and beyond networks, e.g., ones which are similar to known attacks but that are hard to detect through the use of traditional algorithms. More importantly, ML in 5G and beyond security brings novel possibilities in analyzing, modeling and detecting network threats, whilst also enabling the learning of unprecedented attacks in emerging 5G and beyond networks, so that they can be detected and addressed without the need for external resources.

The purpose of this Special Issue is to provide a premier forum for researchers and academics working on ML in 5G and beyond security to present their state-of-the-art research contributions. We invite submissions of high-quality papers in the form of either original research or surveys/overviews, which have not been published previously and are not currently in press, under review or being considered for publication by another journal or conference. Potential topics include, but are not limited to, the following:

  • ML in 5G and beyond security;
  • ML-driven attack model generation and specification;
  • ML for big data security/cloud security/IoT security;
  • ML-based cryptographic protocols in networks;
  • ML-based identity management in 5G and beyond networks;
  • ML for predicting user behavior in 5G and beyond networks;
  • the analysis, modelling and visualization of attacks using ML;
  • security threats, intrusions and malware detection exploiting ML methods;
  • security architectures for heterogeneous 5G and beyond mobile networks;
  • trusted and trustworthy computing for 5G and beyond mobile technologies;
  • the orchestration of SDN or NFV for securing 5G mobile applications;
  • data security for 5G device-to-device (D2D) communications;
  • secure mobile augmented reality (AR)/virtual reality (VR) applications with 5G and beyond networks.

Prof. Dr. Yuanlong Cao
Dr. Bo Wei
Dr. Shuai Zhao
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Electronics is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • 5G and beyond security
  • machine learning
  • data security
  • trusted computing
  • secure mobile augmented reality (AR)/virtual reality (VR)

Published Papers (4 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Research

Jump to: Review

17 pages, 2884 KiB  
Article
A User Purchase Behavior Prediction Method Based on XGBoost
by Wenle Wang, Wentao Xiong, Jing Wang, Lei Tao, Shan Li, Yugen Yi, Xiang Zou and Cui Li
Electronics 2023, 12(9), 2047; https://doi.org/10.3390/electronics12092047 - 28 Apr 2023
Viewed by 2418
Abstract
With the increasing use of electronic commerce, online purchasing users have been rapidly rising. Predicting user behavior has therefore become a vital issue based on the collected data. However, traditional machine learning algorithms for prediction require significant computing time and often produce unsatisfactory [...] Read more.
With the increasing use of electronic commerce, online purchasing users have been rapidly rising. Predicting user behavior has therefore become a vital issue based on the collected data. However, traditional machine learning algorithms for prediction require significant computing time and often produce unsatisfactory results. In this paper, a prediction model based on XGBoost is proposed to predict user purchase behavior. Firstly, a user value model (LDTD) utilizing multi-feature fusion is proposed to differentiate between user types based on the available user account data. The multi-feature behavior fusion is carried out to generate the user tag feature according to user behavior patterns. Next, the XGBoost feature importance model is employed to analyze multi-dimensional features and identify the model with the most significant weight value as the key feature for constructing the model. This feature, together with other user features, is then used for prediction via the XGBoost model. Compared to existing machine learning models such as K-Nearest Neighbor (KNN), Support Vector Machine (SVM), Random Forest (RF), and Back Propagation Neural Network (BPNN), the eXtreme Gradient Boosting (XGBoost) model outperforms with an accuracy of 0.9761, an F1 score of 0.9763, and a ROC value of 0.9768. Thus, the XGBoost model demonstrates superior stability and algorithm efficiency, making it an ideal choice for predicting user purchase behavior with high levels of accuracy. Full article
Show Figures

Figure 1

9 pages, 438 KiB  
Communication
A Network Traffic Anomaly Detection Method Based on Gaussian Mixture Model
by Bin Yu, Yongzheng Zhang, Wenshu Xie, Wenjia Zuo, Yiming Zhao and Yuliang Wei
Electronics 2023, 12(6), 1397; https://doi.org/10.3390/electronics12061397 - 15 Mar 2023
Cited by 2 | Viewed by 1605
Abstract
How can we learn the normal behavior of some communication processes and predict whether a single communication is under attack, with massive network traffic data representing the time costs of each stage in a single communication process? This paper introduces a statistical method [...] Read more.
How can we learn the normal behavior of some communication processes and predict whether a single communication is under attack, with massive network traffic data representing the time costs of each stage in a single communication process? This paper introduces a statistical method for detecting network traffic anomalies using the Gaussian mixture model. There are two aspects to our contributions. First, we show how to learn the normal behavior of a communication process under the assumption that its time costs are generated from the Gaussian mixture model. Secondly, we show that with the learned Gaussian mixture model, we can predict whether a data point is under attack by computing the likelihood that the data point is drawn from the learned Gaussian distribution. The experimental results show that our method reached high accuracy in some cases, while in some other cases that are more complicated, the data point may have more factors and cannot be represented simply by only one Gaussian mixture model. Full article
Show Figures

Figure 1

Review

Jump to: Research

28 pages, 4772 KiB  
Review
Enhancing Smart-Contract Security through Machine Learning: A Survey of Approaches and Techniques
by Fan Jiang, Kailin Chao, Jianmao Xiao, Qinghua Liu, Keyang Gu, Junyi Wu and Yuanlong Cao
Electronics 2023, 12(9), 2046; https://doi.org/10.3390/electronics12092046 - 28 Apr 2023
Cited by 3 | Viewed by 4563
Abstract
As blockchain technology continues to advance, smart contracts, a core component, have increasingly garnered widespread attention. Nevertheless, security concerns associated with smart contracts have become more prominent. Although machine-learning techniques have demonstrated potential in the field of smart-contract security detection, there is still [...] Read more.
As blockchain technology continues to advance, smart contracts, a core component, have increasingly garnered widespread attention. Nevertheless, security concerns associated with smart contracts have become more prominent. Although machine-learning techniques have demonstrated potential in the field of smart-contract security detection, there is still a lack of comprehensive review studies. To address this research gap, this paper innovatively presents a comprehensive investigation of smart-contract vulnerability detection based on machine learning. First, we elucidate common types of smart-contract vulnerabilities and the background of formalized vulnerability detection tools. Subsequently, we conduct an in-depth study and analysis of machine-learning techniques. Next, we collect, screen, and comparatively analyze existing machine-learning-based smart-contract vulnerability detection tools. Finally, we summarize the findings and offer feasible insights into this domain. Full article
Show Figures

Figure 1

18 pages, 351 KiB  
Review
Transportation of Service Enhancement Based on Virtualization Cloud Desktop
by Fan Li, Tengda Guo, Xiaohui Li, Junfeng Wang, Yunni Xia and Yong Ma
Electronics 2023, 12(7), 1572; https://doi.org/10.3390/electronics12071572 - 27 Mar 2023
Cited by 1 | Viewed by 1408
Abstract
Cloud desktop represents an outstanding product in the domain of cloud computing, which refers to the desktop cloud, desktop virtualization and virtual desktop. Cloud desktop explores the virtualization technology to concentrate computing resources, which delivers traditional computer desktops (operating system interfaces) or applications [...] Read more.
Cloud desktop represents an outstanding product in the domain of cloud computing, which refers to the desktop cloud, desktop virtualization and virtual desktop. Cloud desktop explores the virtualization technology to concentrate computing resources, which delivers traditional computer desktops (operating system interfaces) or applications deployed in the pooled computing resources to polymorphic terminals through the Internet. As a distinctive product of cloud computing, cloud desktop has been a hot topic since its inception. Today, the virtualized resource pool of cloud computing achieves the elastic and dynamic expansion of resources, which brings the desktop system from an independent personal computer to a centralized physical server. Consequently, the great improvement in basic network conditions makes it possible to transmit high-quality desktops over the network. There are two key factors for cloud desktops, one of which is the virtualization technology on the server side and the other one, which is the transmission protocol of cloud desktops. The cloud desktop transmission protocol mainly completes the transmission of graphics, images and audio from the server to the user terminal. The transmission of input information from the user terminal, called DaaS (Desktop-as-a-Service), includes the input information of peripherals such as a mouse, keyboard, printer and so on. The efficiency of the transmission protocol determines the basic delivery capability of the cloud desktop, while the bearer protocol and graphics and image processing methods in the transmission protocol determine the interactive experience of the cloud desktop. Different protocols have their characteristics and applicable space. This paper spies on application and transport layer communication protocols to meet DaaS communication requirements. This paper describes the internal mechanism of various transport protocols applicable to a cloud desktop from the principle level and points out the pros and cons and the current application environment. It can be seen that these methods solve the transmission efficiency of burst traffic, improve user experience and reduce bandwidth consumption, which are the development direction of transmission protocols. Full article
Show Figures

Figure 1

Back to TopTop