Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
5.3
2.6
Journals
Electronics
Special Issues
Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from...
share announcement

Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0

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

Deadline for manuscript submissions: closed (15 August 2024) | Viewed by 10547

Special Issue Editors

Dr. Yuhang Ye

E-Mail Website
Guest Editor
Software Research Institute, N37 A3W4 Athlone, Ireland
Interests: network security; machine learning; network traffic control; multimedia communication
Dr. Nadia Kanwal

E-Mail Website
Guest Editor
School of Computer Science and Mathematics, Keele University, Staffordshire ST5 5GB, UK
Interests: machine learning; computer vision; image processing; visual data; privacy; security; object classification; activity recognition; medical image analysis
Special Issues, Collections and Topics in MDPI journals
Dr. Brian Lee

E-Mail Website
Guest Editor
Software Research Institute, Technological University of The Shannon, Midlands Midwest, N37 HD68 Athlone, Ireland
Interests: network security; machine learning; robotic control; network management; edge computing; IoT
Dr. Mohammad Samar Ansari

E-Mail Website
Guest Editor
Physical, Mathematical and Engineering Sciences, University of Chester, Parkgate Road, Chester CH1 4BJ, UK
Interests: neural networks; deep learning; IoT; smart cities; resource-efficient machine learning
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

As we embrace the digital revolution brought by Industry 4.0, cybersecurity has emerged as a crucial area of concern. In this dynamic landscape, machine learning (ML) and deep learning (DL) technologies have shown tremendous promise in addressing the complexity and scale of cybersecurity issues yet have also introduced novel vulnerabilities. To navigate this double-edged sword, we must foster a deeper understanding of the intersection of ML, DL, and cybersecurity.

In this Special Issue, titled "Machine Learning Security in Industry 4.0: Opportunities, Challenges, and Innovations," we invite scholars and professionals from around the globe to share their cutting-edge research, innovative strategies, and insightful experiences. We aim to create a knowledge hub that sparks exciting discussions, advances scientific understanding, and catalyzes transformative solutions for securing our digital future.

The Special Issue will spotlight a broad spectrum of research areas, including:

  • Innovative Intrusion Detection Models: Can we leverage the power of ML to design more efficient and effective intrusion detection systems? We seek pioneering works that break the mold, exploring novel ML algorithms and architectures for anomaly detection and cybersecurity breach prevention.
  • Revolutionizing Risk Assessment: How can ML help predict and quantify the potential impact of cyber threats? We invite visionary contributions that redefine risk assessment paradigms, harnessing ML to identify, analyze, and mitigate cybersecurity risks in industrial systems.
  • Automated Incident Response and Playbook Design: How might ML transform our approach to incident response? This is an open call for revolutionary ideas that integrate ML into incident response strategies and playbook design, enabling rapid, intelligent responses to cyber incidents.
  • Next-Level Threat Intelligence Sharing: Can ML facilitate real-time, comprehensive threat intelligence sharing? We welcome groundbreaking research on ML-driven platforms that foster seamless information exchange, building robust, collaborative defenses against emerging threats.
  • Securing ML Models Against Cyber Attacks: How can we safeguard our ML models from adversarial manipulation? We are eager to showcase ingenious research on identifying and thwarting potential attack vectors, including adversarial and backdoor attacks on neural networks. Adversarial: The Role of Large Language Models in Cybersecurity: What unique possibilities and challenges do advanced models such as GPT series bring to the cybersecurity landscape? We invite forward-thinking explorations on employing large language models for threat detection, phishing detection, and other cybersecurity applications.

We welcome submissions in various formats, from original research and review articles to case studies and more. Each contribution will be an integral part of our collective endeavor to advance this vital field, inspiring fellow researchers, guiding policy-makers, and ultimately safeguarding our Industry 4.0 systems.

Join us in this exciting quest to illuminate the frontiers of Machine Learning Security in Industry 4.0 and shape the future of cybersecurity. Your insights could be the catalyst for the next big breakthrough in this fast-evolving field.

Dr. Yuhang Ye
Dr. Nadia Kanwal
Dr. Brian Lee
Dr. Mohammad Samar Ansari
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

  • backdoor
  • adversarial learning
  • cybersecurity
  • Industry 4.0 industrial control system
  • ICS
  • SCADA
  • risk assessment
  • digital twin
  • trigger
  • data poisoning
  • model poisoning
  • overfitting
  • model robustness

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue polices can be found here.

Published Papers (6 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

19 pages, 6135 KiB  
Article
Integration of Legacy Industrial Equipment in a Building-Management System Industry 5.0 Scenario
by Adrian Korodi, Ioana-Victoria Nițulescu, Adriana-Anamaria Fülöp, Vlad-Cristian Vesa, Petru Demian, Robert-Adelin Braneci and Daniel Popescu
Electronics 2024, 13(16), 3229; https://doi.org/10.3390/electronics13163229 - 15 Aug 2024
Viewed by 1150
Abstract
Considering Industry 4.0 directions, followed by recent Industry 5.0 principles, interest in integrating legacy systems in industrial manufacturing has emerged. Due to the continuous evolution of the Internet of Things (IoT) and the Industrial Internet of Things (IIoT), as well as the rapid [...] Read more.
Considering Industry 4.0 directions, followed by recent Industry 5.0 principles, interest in integrating legacy systems in industrial manufacturing has emerged. Due to the continuous evolution of the Internet of Things (IoT) and the Industrial Internet of Things (IIoT), as well as the rapid extension of the scope and adoption of broader technologies, such integration has become feasible. Even though newly developed equipment provides easier interoperability, the replacement of legacy systems highly impacts cost and sustainability, which usually extends to the entire production process, the operators and the maintenance team, and sometimes even the robustness of the production process. Ensuring the interoperability of legacy systems is a problematic task, being dependent on technologies and development techniques and specific industrial domain particularities. This paper considers strategies to ensure the interoperability of legacy systems in a building-management system scenario where local structures are approached using both industrial protocols and web-based contexts. The solution is built following the Industry 5.0 pillars (sustainability, human focus, resilience) and conceives the entire data acquisition and supervisory solution to be flexible, open-source, resilient, and under the control of company engineers. The chosen environment for interfacing and supervision is Node-RED, enabling IoT and IIoT tools, together with a complete orientation toward digital transformation. This way, it is possible to construct a final result that enhances security while bridging outdated protocols and technologies, eliminating compatibility risks in the context of the evolutionary IIoT, ensuring critical process functions are possible, and aiding operators in complying with regulations governing building-management system (BMS) operations, thus solving the challenges that arise in the complex task of adopting the IoT backbone of digital transformation in relation to the integration of legacy equipment. The obtained solution is tested in an automotive industry building-management system, and the results demonstrate its performance, reliability, and high customizability in a context of openness and low cost. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0)
►▼ Show Figures

Figure 1

21 pages, 7977 KiB  
Article
Forensic Analysis for Cybersecurity of Smart Home Environments with Smart Wallpads
by Sungbum Kim, Jewan Bang and Taeshik Shon
Electronics 2024, 13(14), 2827; https://doi.org/10.3390/electronics13142827 - 18 Jul 2024
Viewed by 901
Abstract
Various smart home companies are adding displays to smart home control devices and are also releasing smart home control functions for devices with displays. Since smart home management devices with displays are multifunctional, they can store more digital evidence than traditional management devices. [...] Read more.
Various smart home companies are adding displays to smart home control devices and are also releasing smart home control functions for devices with displays. Since smart home management devices with displays are multifunctional, they can store more digital evidence than traditional management devices. Therefore, we propose a smart home environment forensic methodology focused on wallpads, which are smart home management devices with displays. And we validate the proposed methodology by building a smart home environment centered around wallpads and conducting tests with three vendors (Samsung, Kocom, and Commax). Following the proposed methodology, we identified the software and hardware specifications of devices within the testbed, particularly the wallpads. Based on this, we were able to extract network packets, disk images, and individual files stored internally using methods such as packet capture, vulnerability exploits, serial ports, and chip-off. Through analysis, we confirmed that significant user-related information and videos are stored in these control devices. The digital evidence obtained through the proposed methodology can be used as critical legal evidence, and this study contributes to efficiently analyzing important security issues and evidential data in various smart home IoT environments. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0)
►▼ Show Figures

Figure 1

21 pages, 3840 KiB  
Article
Digital Forensics for Analyzing Cyber Threats in the XR Technology Ecosystem within Digital Twins
by Subin Oh and Taeshik Shon
Electronics 2024, 13(13), 2653; https://doi.org/10.3390/electronics13132653 - 6 Jul 2024
Viewed by 1200
Abstract
Recently, advancements in digital twin and extended reality (XR) technologies, along with industrial control systems (ICSs), have driven the transition to Industry 5.0. Digital twins mimic and simulate real-world systems and play a crucial role in various industries. XR provides innovative user experiences [...] Read more.
Recently, advancements in digital twin and extended reality (XR) technologies, along with industrial control systems (ICSs), have driven the transition to Industry 5.0. Digital twins mimic and simulate real-world systems and play a crucial role in various industries. XR provides innovative user experiences through virtual reality (VR), augmented reality (AR), and mixed reality (MR). By integrating digital twin simulations into XR devices, these technologies are utilized in various industrial fields. However, the prevalence of XR devices has increased the exposure to cybersecurity threats in ICS and digital twin environments. Because XR devices are connected to networks, the control and production data they process are at risk of being exposed to cyberattackers. Attackers can infiltrate XR devices through malicious code or hacking attacks to take control of the ICS or digital twin or paralyze the system. Therefore, this study emphasizes the cybersecurity threats in the ecosystem of XR devices used in ICSs and conducts research based on digital forensics. It identifies potentially sensitive data and artifacts in XR devices and proposes secure and reliable security response measures in the Industry 5.0 environment. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0)
►▼ Show Figures

Figure 1

17 pages, 1618 KiB  
Article
Two-Phase Industrial Control System Anomaly Detection Using Communication Patterns and Deep Learning
by Sungjin Kim, Wooyeon Jo, Hyunjin Kim, Seokmin Choi, Da-I Jung, Hyeonho Choi and Taeshik Shon
Electronics 2024, 13(8), 1520; https://doi.org/10.3390/electronics13081520 - 17 Apr 2024
Cited by 1 | Viewed by 870
Abstract
Several cases of Industrial Internet of Things (IIoT) attacks with zero-day vulnerabilities have been reported. To prevent these attacks, it is necessary to apply an abnormal behavior detection method; however, there are three main problems that make it hard. First, there are various [...] Read more.
Several cases of Industrial Internet of Things (IIoT) attacks with zero-day vulnerabilities have been reported. To prevent these attacks, it is necessary to apply an abnormal behavior detection method; however, there are three main problems that make it hard. First, there are various industrial communication protocols. Instead of IT environments, many unstandardized protocols, which are usually defined by vendors, are used. Second, legacy devices are commonly used, not only EOS (End-of-service), but also EoL (End-of-Life). And last, the analysis of collected data is necessary for defining normal behavior. This behavior should be separately defined in each IIoT. Therefore, it is difficult to apply abnormal behavior detection in environments where economic and human investment is difficult. To solve these problems, we propose a deep learning based abnormal behavior detection technique that utilizes IIoT communication patterns. The proposed method uses a deep learning technique to train periodic data acquisition sequences, which is one of the common characteristics of IIoT. The trained model determined the sequence of packet is normal. The proposed technique can be applied without an additional analysis. The proposed method is expected to prevent security threats by proactively detecting cyberattacks. To verify the proposed method, a dataset was collected from the Korea Electric Power Control System. The model that defines normal behavior based on the application layer exhibits an accuracy of 79.6%. The other model, defining normal behavior based on the transport layer, has an accuracy of 80.9%. In these two models, most false positives and false negatives only occur when the abnormal packet is in a sequence. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0)
►▼ Show Figures

Figure 1

28 pages, 4406 KiB  
Article
Bridging the Cybersecurity Gap: A Comprehensive Analysis of Threats to Power Systems, Water Storage, and Gas Network Industrial Control and Automation Systems
by Thierno Gueye, Asif Iqbal, Yanen Wang, Ray Tahir Mushtaq and Mohd Iskandar Petra
Electronics 2024, 13(5), 837; https://doi.org/10.3390/electronics13050837 - 21 Feb 2024
Viewed by 1956
Abstract
This research addresses the dearth of real-world data required for effective neural network model building, delving into the crucial field of industrial control and automation system (ICS) cybersecurity. Cyberattacks against ICS are first identified and then generated in an effort to raise awareness [...] Read more.
This research addresses the dearth of real-world data required for effective neural network model building, delving into the crucial field of industrial control and automation system (ICS) cybersecurity. Cyberattacks against ICS are first identified and then generated in an effort to raise awareness of vulnerabilities and improve security. This research aims to fill a need in the existing literature by examining the effectiveness of a novel approach to ICS cybersecurity that draws on data from real industrial settings. Real-world data from a variety of commercial sectors is used in this study to produce a complete dataset. These sectors include power systems, freshwater tanks, and gas pipelines, which together provide a wide range of commercial scenarios where anomaly detection and attack classification approaches are critical. The generated data are shown to considerably improve the models’ precision. An amazing 71% accuracy rate is achieved in power system models, and incorporating generated data reliably increases network speed. Using generated data, the machine learning system achieves an impressive 99% accuracy in a number of trials. In addition, the system shows about 90% accuracy in most studies when applied to the setting of gas pipelines. In conclusion, this article stresses the need to improve cybersecurity in vital industrial sectors by addressing the dearth of real-world ICS data. To better understand and defend against cyberattacks on industrial machinery and automation systems, it demonstrates how generative data can improve the precision and dependability of neural network models. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0)
►▼ Show Figures

Figure 1

Review

Jump to: Research

15 pages, 443 KiB  
Review
AI in IIoT Management of Cybersecurity for Industry 4.0 and Industry 5.0 Purposes
by Grzegorz Czeczot, Izabela Rojek, Dariusz Mikołajewski and Belco Sangho
Electronics 2023, 12(18), 3800; https://doi.org/10.3390/electronics12183800 - 8 Sep 2023
Cited by 15 | Viewed by 3454
Abstract
If we look at the chronology of transitions between successive stages of industrialization, it is impossible not to notice a significant acceleration. There were 100 years between the industrial revolutions from 2.0 to 3.0, and only half a century passed from the conventional [...] Read more.
If we look at the chronology of transitions between successive stages of industrialization, it is impossible not to notice a significant acceleration. There were 100 years between the industrial revolutions from 2.0 to 3.0, and only half a century passed from the conventional 3.0 to 4.0. Assuming that progress will inevitably continue to accelerate, and given that 2011 is the set date for the start of the fourth industrial revolution, we can expect Industry 5.0 by 2035. In recent years, Industrial Internet of Things (IIoT) applications proliferated, which include multiple network elements connected by wired and wireless communication technologies, as well as sensors and actuators placed in strategic locations. The significant pace of development of the industry of advantages in predicting threats to infrastructure will be related to the speed of analyzing the huge amount of data on threats collected not locally, but globally. This article sheds light on the potential role of artificial intelligence (AI) techniques, including machine learning (ML) and deep learning (DL), to significantly impact IIoT cyber threat prediction in Industry 5.0. Full article
(This article belongs to the Special Issue Artificial Intelligence and Machine Learning in Cybersecurity Frontiers: Insights from Industry 4.0 and Innovations for Industry 5.0)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-6
Back to TopTop