AI-Enabled Cyber Defence in IoT Deployments: Challenges and Opportunities

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Electrical, Electronics and Communications Engineering".

Deadline for manuscript submissions: closed (30 December 2023) | Viewed by 7066

Special Issue Editors

Prof. Dr. Carsten R. Maple
E-Mail Website
Guest Editor
WMG, University of Warwick, Coventry, UK
Interests: cyber-physical systems; cyber resilience
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

As a result of the massive growth in cyber threats, the operational environment is rapidly shifting, resulting in major gaps in cyber decision-making skills with regard to defence. The existing legal and regulatory compliance procedures were not intended to work in cyberspace, increasing the need for cyber-resilient, mission-critical systems. Cyber–physical systems and the Internet of Things have developed as a new battlefield in warfare, with assaults against them no longer restricted to cyberspace. This tendency is further supported by our limited ability to precisely evaluate the immediate security risk of these mission-critical systems, given the fast change and variety of threat landscapes and related vulnerabilities in contemporary cyberspaces. In addition, the majority of our legacy cyber–physical systems are only protected in isolation from the designs of the information systems with which they must eventually interact with. The transition and sustainability of these structures demand a broader system design approach as a reference for the interaction of these systems with networks and for comprehensive security from component-level to systems-level integration of cyberspace-enabled applications.

This Special Issue focuses on emerging topics in employing intelligent operations, algorithms, and processes that support a broad range of applications, with an emphasis on the following research directions: (a) IoT cyber resilience; (b) risk-and-attack surface-exposure analyses; (c) security management processes and legal and regulatory implications in modern cyberinfrastructures; (d) AI-enabled cyber threats and proactive defences.

This Special Issue is devoted to presenting cutting-edge research addressing the many research trends and concerns in utilising AI to defend modern cyberinfrastructures, as well as providing academics and practitioners with valuable insights into the efficiencies of these innovations in modern cyber defence. 

Topics of interest for this Special Issue include, but are not limited to, the following:

  • Cyber resilience and system security assessments using AI;
  • Cyber security risk in transdisciplinary settings;
  • DL-based cyberthreat and effects modelling;
  • Cyber defence taxonomy and DL-enabled risk-estimation models;
  • AI-enhanced cyber threats and defences;
  • Advancements in RegTech services for IoT;
  • Cyber modeling and simulation for cyber incident analysis;
  • Privacy and data control using intelligent operations;
  • Secure quantum communications;
  • Adversarial machine learning;
  • IoT/CPS cybersecurity;
  • Distributed technologies for defensive cyber operations;
  • Intelligent threat network degradation
  • Cyber law and ethics;
  • Cyberthreat information presentation
  • Cyber threat intelligence- and information-acquisition systems;
  • Compliance-aware security engineering.

Dr. Gregory Epiphaniou
Prof. Dr. Carsten R. Maple
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. Applied Sciences 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

  • CPS
  • IoT
  • AI
  • threat and risk modelling
  • DLT
  • cyber defence

Published Papers (4 papers)

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

Research

44 pages, 1689 KiB  
Article
A Survey on Cyber Risk Management for the Internet of Things
Appl. Sci. 2023, 13(15), 9032; https://doi.org/10.3390/app13159032 - 07 Aug 2023
Cited by 1 | Viewed by 1113
Abstract
The Internet of Things (IoT) continues to grow at a rapid pace, becoming integrated into the daily operations of individuals and organisations. IoT systems automate crucial services within daily life that users may rely on, which makes the assurance of security towards entities [...] Read more.
The Internet of Things (IoT) continues to grow at a rapid pace, becoming integrated into the daily operations of individuals and organisations. IoT systems automate crucial services within daily life that users may rely on, which makes the assurance of security towards entities such as devices and information even more significant. In this paper, we present a comprehensive survey of papers that model cyber risk management processes within the context of IoT, and provide recommendations for further work. Using 39 collected papers, we studied IoT cyber risk management frameworks against four research questions that delve into cyber risk management concepts and human-orientated vulnerabilities. The importance of this work being human-driven is to better understand how individuals can affect risk and the ways that humans can be impacted by attacks within different IoT domains. Through the analysis, we identified open areas for future research and ideas that researchers should consider. Full article
Show Figures

Figure 1

17 pages, 6255 KiB  
Article
Optimal Graph Convolutional Neural Network-Based Ransomware Detection for Cybersecurity in IoT Environment
Appl. Sci. 2023, 13(8), 5167; https://doi.org/10.3390/app13085167 - 21 Apr 2023
Cited by 6 | Viewed by 1422
Abstract
The fast development of the Internet of Things (IoT) and widespread utilization in a large number of areas, such as vehicle IoT, industrial control, healthcare, and smart homes, has made IoT security increasingly prominent. Ransomware is a type of malware which encrypts the [...] Read more.
The fast development of the Internet of Things (IoT) and widespread utilization in a large number of areas, such as vehicle IoT, industrial control, healthcare, and smart homes, has made IoT security increasingly prominent. Ransomware is a type of malware which encrypts the victim’s records and demands a ransom payment for restoring access. The effective detection of ransomware attacks highly depends on how its traits are discovered and how precisely its activities are understood. In this article, we propose an Optimal Graph Convolutional Neural Network based Ransomware Detection (OGCNN-RWD) technique for cybersecurity in an IoT environment. The OGCNN-RWD technique involves learning enthusiasm for teaching learning-based optimization (LETLBO) algorithms for the feature subset selection process. For ransomware classification, the GCNN model is used in this study, and its hyperparameters can be optimally chosen by the harmony search algorithm (HSA). For exhibiting the greater performance of the OGCNN-RWD approach, a series of simulations were made on the ransomware database. The simulation result portrays the betterment of the OGCNN-RWD system over other existing techniques with an accuracy of 99.64%. Full article
Show Figures

Figure 1

22 pages, 2707 KiB  
Article
Reducing False Negatives in Ransomware Detection: A Critical Evaluation of Machine Learning Algorithms
Appl. Sci. 2022, 12(24), 12941; https://doi.org/10.3390/app122412941 - 16 Dec 2022
Cited by 2 | Viewed by 2157
Abstract
Technological achievement and cybercriminal methodology are two parallel growing paths; protocols such as Tor and i2p (designed to offer confidentiality and anonymity) are being utilised to run ransomware companies operating under a Ransomware as a Service (RaaS) model. RaaS enables criminals with a [...] Read more.
Technological achievement and cybercriminal methodology are two parallel growing paths; protocols such as Tor and i2p (designed to offer confidentiality and anonymity) are being utilised to run ransomware companies operating under a Ransomware as a Service (RaaS) model. RaaS enables criminals with a limited technical ability to launch ransomware attacks. Several recent high-profile cases, such as the Colonial Pipeline attack and JBS Foods, involved forcing companies to pay enormous amounts of ransom money, indicating the difficulty for organisations of recovering from these attacks using traditional means, such as restoring backup systems. Hence, this is the benefit of intelligent early ransomware detection and eradication. This study offers a critical review of the literature on how we can use state-of-the-art machine learning (ML) models to detect ransomware. However, the results uncovered a tendency of previous works to report precision while overlooking the importance of other values in the confusion matrices, such as false negatives. Therefore, we also contribute a critical evaluation of ML models using a dataset of 730 malware and 735 benign samples to evaluate their suitability to mitigate ransomware at different stages of a detection system architecture and what that means in terms of cost. For example, the results have shown that an Artificial Neural Network (ANN) model will be the most suitable as it achieves the highest precision of 98.65%, a Youden’s index of 0.94, and a net benefit of 76.27%, however, the Random Forest model (lower precision of 92.73%) offered the benefit of having the lowest false-negative rate (0.00%). The risk of a false negative in this type of system is comparable to the unpredictable but typically large cost of ransomware infection, in comparison with the more predictable cost of the resources needed to filter false positives. Full article
Show Figures

Figure 1

15 pages, 799 KiB  
Article
Preliminary Examination of Emergent Threat and Risk Landscapes in Intelligent Harvesting Robots
Appl. Sci. 2022, 12(24), 12931; https://doi.org/10.3390/app122412931 - 16 Dec 2022
Viewed by 1007
Abstract
Recently, many farmers have started using robots to help with labour-intensive harvesting operations and deal with labour shortage that was also a negative consequence of the recent COVID-19 pandemic. Intelligent harvesting robots make farming more efficient and productive. However, and like any other [...] Read more.
Recently, many farmers have started using robots to help with labour-intensive harvesting operations and deal with labour shortage that was also a negative consequence of the recent COVID-19 pandemic. Intelligent harvesting robots make farming more efficient and productive. However, and like any other technology, intelligent harvesting robots come with a security risk, as threats can damage the robotic system and wreak havoc before the farmer/operator realizes it. This paper focuses on analysing the threats against the security of harvesting robots alongside with the safety implications that may rise if the robotic system is compromised. We analysed an actual asparagus harvesting robot and looked at others in the literature. We identified several security threats which we classified into five categories: network, hardware, software, Artificial Intelligence (AI) and cloud security issues. We selected three interesting attack scenarios for a deeper analysis. Our results suggest that these robots have a large attack surface that can lead to exploits with immense financial and operational impacts. Full article
Show Figures

Figure 1

Back to TopTop