Cybersecurity Systems Research Articles

CySecBERT : A Domain-Adapted Language Model for the Cybersecurity Domain

The field of cysec is evolving fast. Security professionals are in need of intelligence on past, current and —ideally — upcoming threats, because attacks are becoming more advanced and are increasingly targeting larger and more complex systems. Since the processing and analysis of such large amounts of information cannot be addressed manually, cysec experts rely on machine learning techniques. In the textual domain, pre-trained language models such as Bidirectional Encoder Representations from Transformers (BERT) have proven to be helpful as they provide a good baseline for further fine-tuning. However, due to the domain-knowledge and the many technical terms in cysec, general language models might miss the gist of textual information. For this reason, we create a high-quality dataset 1 and present a language model 2 specifically tailored to the cysec domain that can serve as a basic building block for cybersecurity systems. The model is compared on 15 tasks: Domain-dependent extrinsic tasks for measuring the performance on specific problems, intrinsic tasks for measuring the performance of the internal representations of the model, as well as general tasks from the SuperGLUE benchmark. The results of the intrinsic tasks show that our model improves the internal representation space of domain words compared with the other models. The extrinsic, domain-dependent tasks, consisting of sequence tagging and classification, show that the model performs best in cybersecurity scenarios. In addition, we pay special attention to the choice of hyperparameters against catastrophic forgetting, as pre-trained models tend to forget the original knowledge during further training.

Cybersecurity of Industrial Systems—A 2023 Report

The article explores the importance of cybersecurity in Industry 4.0, specifically focusing on safeguarding industrial automation systems from cyberattacks. It discusses essential security measures, network monitoring, and employee training, emphasizing the significance of risk management for ensuring industry stability. Adherence to industrial security standards, such as ISA/IEC 62443, is crucial (ISA—International Society of Automation, IEC—International Electrotechnical Commission). The article outlines cyberthreat challenges and their impact on various sectors, including healthcare and finance, as well as the risks faced by large industrial enterprises. Additionally, it elucidates evolving cybersecurity strategies and principles, underscoring the necessity for continuous, multi-layered protection. Collaboration with operators, strict information security policies, and robust incident response plans are emphasized. The importance of risk monitoring and adaptability to ever-changing threat landscapes is highlighted, emphasizing the collaborative and flexible nature of cybersecurity in the face of escalating digital threats.

Правові аспекти забезпечення кібербезпеки в Україні: сучасні виклики та роль національного законодавства

The article identifies the peculiarities of the current state of cybersecurity in Ukraine and emphasizes the importance of applying effective legislation aimed at protecting the cyber structure, as well as choosing the best tools and mechanisms to combat cyber threats. For the purpose of this study, the author has selected the national legislation aimed at regulating the cybersecurity sector. The key aspects of legislation affecting cybersecurity and protection of information resources of Ukraine, in particular in the context of current challenges and threats of modern cyberspace, are quite effective today, as evidenced by the results of statistics on solving problems related to hacker attacks on Ukraine during the military conflict in 2022–2024. However, despite the fact that the current legislative acts create a solid basis for the development of Ukraine’s cybersecurity system, the article discusses issues that remain unresolved. In particular, the role of artificial intelligence in the field of data protection against cyberattacks in the current environment. The role of international cooperation in ensuring cybersecurity is also considered as one of the necessary conditions for ensuring the national security protection system of Ukraine.

Review of Machine learning: Views, Architectures or Techniques, Challenges and Future guidance and Real-world applications

In this digital world, the data is wealth, this data is analyzed, developed and applied to specific applications using some well-developed algorithms known as Machine learning (ML). Machine learning algorithms are supervised, unsupervised, semi-supervised and reinforcement types. Deep learning (DL) is also a method of analyzing the data on a large scale. Deep learning is a further subdivision of The subsection of ML is deep learning and measures a particular type of learning that involves the use of artificial neural networks (ANN). This paper provides group of different machine learning terminologies for quick reference. This study is important to focus on different machine learning techniques and their connection in various real-world applications such as smart cities, cyber security, healthcare, agriculture and intelligent transportation systems. In this paper, machine learning concepts, different types of architectures, the challenges, various real world applications are discussed.

Analysis of the Impact of Cybersecurity on the Stability of Financial Institutions

"The issue of the impact of cybersecurity is a top priority for the functioning of a financial institution. Therefore, its provision becomes a priority in organizing the further activities of the institution itself. The article aims to analyze the current trends in ensuring the cybersecurity of financial institutions and its role in their functioning. The paper describes the theoretical foundations of the cyber protection concept. The authors also outline the specifics of cybersecurity and the leading technological solutions for achieving these goals. Special attention is paid to modern, innovative solutions to maintain the stability of financial institutions and the possibility of further development. An important area of research is the disclosure of the practical experience of information corporations in providing technical solutions to ensure the security of financial transactions and support the global financial system. The study presents the experience of Ukrainian financial institutions that use variable digital defense strategies and maintain their functionality based on an effective cybersecurity system in the context of a global military conflict. The results of the study include a detailed profile of effective practical solutions to ensure the stability of financial institutions based on the implementation of blockchain technologies. The authors pay attention to the issue of modern software, hardware, and management solutions to improve the quality of cybersecurity in the context of growing cyberattacks and digital threats to the stability of financial institutions. The research findings may be helpful for further analytical studies on the effectiveness of cybersecurity and the stability of financial institutions."

Augmenting cybersecurity in smart urban energy systems through IoT and blockchain technology within the Digital Twin framework

This research presents a comprehensive framework to enhance the cybersecurity and efficiency of smart urban energy systems by integrating cutting-edge technologies. Leveraging advanced evolutionary optimization techniques, specifically Covariance Matrix Adaptation Evolution Strategy (CMA-ES), the proposed system optimizes energy management and trading within urban infrastructure. Simultaneously, the integration of Internet of Things (IoT) devices enables real-time monitoring and decision-making, while blockchain technology ensures secure and transparent transactions. The study evaluates system performance by comparing it with traditional approaches, assessing key metrics such as convergence speed, exploration, exploitation, and cybersecurity. Results indicate that the proposed framework outperforms traditional systems in energy efficiency, cost-effectiveness, and cybersecurity metrics. This research offers valuable insights into integrating emerging technologies to address evolving challenges in smart urban energy systems. The findings highlight the potential of this innovative framework to revolutionize urban energy management, providing a foundation for more resilient, secure, and efficient smart cities. As the global urban landscape continues to evolve, this framework represents a strategic approach to meet the increasing demands for sustainable and secure urban energy solutions.

Closing Disparities in Intrusion Detection: An In-Depth Analysis of IDPS Systems

Intrusion detection systems (IDS) are an important security tool that protects networks by monitoring policy breaches and possible threat activities Over the years, IDS technology has advanced significantly to combat cybercrime a it goes forward. The purpose of this paper is to provide a comprehensive review of IDS technology, addressing implementation challenges, research limitations, and future directions. By exploring the various research sub-categories in IDS, readers will gain insight into industry needs and the importance of ongoing research efforts Keywords: Intrusion Detection System (IDS), Threat Detection, Attackers, Network Security, Cybersecurity Systems AIMS-MATHS JOURNAL REFERENCE FORMAT Olasegi, I.G. (2024 Closing Disparities in Intrusion Detection: An In-Depth Analysis of IDPS Systems. Journal of Advances in Mathematical & Computational Science. Vol. 12, No. 1. Pp 100-108. Available online at www.isteams.net/mathematics-computationaljournal. dx.doi.org/10.22624/AIMS/MATHS/V12N1P8

Optimizing E-Government Cybersecurity through Artificial Intelligence Integration

This study explores the integration of Artificial Intelligence (AI) into e-governance cybersecurity, focusing on its key insights, contributions, challenges, and future directions. AI-powered cybersecurity systems offer advanced capabilities in threat detection, response, and scalability, improving the protection of critical infrastructure and sensitive data in government digital services. However, ethical considerations such as transparency, fairness, and accountability, as well as challenges related to algorithm biases, data privacy, and cybersecurity skills gap, must be addressed to ensure responsible and effective use of AI technologies. Recommendations for policymakers, government agencies, and researchers are provided to maximize the benefits of AI while mitigating potential risks and enhancing e-governance cybersecurity resilience in the digital age.

Analysis of modern intelligent methods for protecting critical information infrastructure

Critical information infrastructure (CII), including the financial sector, plays a key role in ensuring the sustainable functioning of economic systems and the financial stability of States. However, the growing digitalization of the financial industry and the introduction of innovative technologies are opening up new attack vectors for attackers. Modern cyber attacks are becoming more sophisticated, and traditional defenses are proving ineffective against new, previously unknown threats. There is an urgent need for more flexible and intelligent cybersecurity systems. Thus, the subject of the study is modern intelligent methods and technologies for protecting critical information infrastructure (CII) from cyber attacks. The object of the research is methods and means of ensuring the protection of critical information infrastructure using artificial intelligence and machine learning technologies. The methodological basis of this study is a comprehensive analysis of the scientific literature on the use of intelligent methods and technologies to protect critical information infrastructure. During the review and critical analysis of relevant scientific publications, key problems and unresolved tasks requiring further scientific research and practical developments in this subject area were identified. This methodological approach allowed us to form a holistic view of the current state and prospects for the development of intelligent cybersecurity tools for critical financial systems, as well as to identify priority areas for further research. The main directions of scientific novelty of this research are: 1. A detailed review of promising approaches based on artificial intelligence and machine learning technologies to ensure effective protection of CII organizations from modern complex cyber attacks. 2. Identification and analysis of a number of key scientific and technical problems that need to be solved to increase reliability, interpretability and trust in intelligent cybersecurity systems, including issues of robustness to attacks, active online learning, federated and differential private data processing. 3. Identification of promising areas for further research and development in the field of application of specialized methods of secure and trusted AI to protect critical financial infrastructure. Thus, this research makes a significant contribution to the development of scientific and methodological apparatus and practical solutions for the use of intelligent methods to ensure cybersecurity.

Detecting Anomalies and Intrusions in Unstructured Cybersecurity Data Using Natural Language Processing

Abstract: Due to the growing volume and variety in data generated by cybersecurity systems, it is crucial that unstructured text be used for detecting anomalies. Natural language processing is a powerful tool for analyzing unstructured information and identifying threats. This paper presents a comprehensive review of NLP applications for cybersecurity. We first present the motivations for and challenges associated with using NLP to improve cybersecurity. Then, we provide background information on unstructured data that is relevant to cybersecurity, and discuss NLP techniques such as named entity recognition (NEAR), sentiment analysis, topic modelling, and document classifying. This paper focuses on how these techniques are used to detect anomalies and intrusions. We present a taxonomy for NLP-driven approaches, and we conduct a literature review that is categorized according to this taxonomy. We examine critically the strengths and weaknesses of current techniques. We highlight research gaps based on this analysis and propose a research agenda to advance NLP research in cybersecurity applications. This paper summarizes previous research and lays the foundation for using NLP to tackle cybersecurity challenges that involve unstructured data.

Cyber5Gym: An Integrated Framework for 5G Cybersecurity Training

The rapid evolution of 5G technology, while offering substantial benefits, concurrently presents complex cybersecurity challenges. Current cybersecurity systems often fall short in addressing challenges such as the lack of realism of the 5G network, the limited scope of attack scenarios, the absence of countermeasures, the lack of reproducible, and open-sourced cybersecurity training environments. Addressing these challenges necessitates innovative cybersecurity training systems, referred to as “cyber ranges”. In response to filling these gaps, we propose the Cyber5Gym, an integrated cyber range that enhances the automation of virtualized cybersecurity training in 5G networks with cloud-based deployment. Our framework leverages open-source tools (i) Open5GS and UERANSIM for realistic emulation of 5G networks, (ii) Docker for efficient virtualization of the training infrastructure, (iii) 5Greply for emulating attack scenarios, and (iv) Shell scripts for automating complex training operations. This integration facilitates a dynamic learning environment where cybersecurity professionals can engage in real-time attack and countermeasure exercises, thus significantly improving their readiness against 5G-specific cyber threats. We evaluated it by deploying our framework on Naver Cloud with 20 trainees, each accessing an emulated 5G network and managing 100 user equipments (UEs), emulating three distinct attack scenarios (SMC-Reply, DoS, and DDoS attacks), and exercising countermeasures, to demonstrate the cybersecurity training. We assessed the effectiveness of our framework through specific metrics such as successfully establishing the 5G network for all trainees, accurate execution of attack scenarios, and their countermeasure implementation via centralized control of the master using automated shell scripts. The open-source foundation of our framework ensures replicability and adaptability, addressing a critical gap in current cybersecurity training methodologies and contributing significantly to the resilience and security of 5G infrastructures.

Effect of Adopting AI to Explore Big Data on Personally Identifiable Information (PII) for Financial and Economic Data Transformation

The integration of Artificial Intelligence (AI) into big data analytics represents a pivotal shift in the management of Personally Identifiable Information (PII) within the financial sector. This study was prompted by the increasing reliance on AI for handling sensitive financial data and the consequent rise in data security concerns, exemplified by the 2019 Capital One data breach which compromised the PII of over 100 million individuals, highlighting the vulnerabilities inherent in digital data storage and management systems. Aiming to critically evaluate the effects of adopting AI in exploring big data on PII within the financial and economic sectors, the study focused on assessing how AI can transform data management processes, enhance data security, ensure compliance with regulatory requirements, and maintain data integrity. Employing a quantitative research methodology, data was gathered from 532 professionals in the financial sector through surveys distributed via LinkedIn. The hypotheses were tested using multiple regression analysis. The study's findings revealed that the adoption of AI in managing big data significantly enhances the security and privacy of PII in the financial sector. However, it also increases the risk of sophisticated cyber-attacks such as adversarial attacks and data poisoning. Significantly, financial institutions that integrate AI into their data management systems demonstrate higher compliance with data protection regulations, and AI-driven cybersecurity strategies were found to markedly improve the performance of cybersecurity systems in the sector. Based on these insights, the study recommends best practices and guidelines for financial institutions to effectively integrate AI into their data management systems. These include prioritizing data security and privacy, ensuring regulatory compliance, investing in AI-driven cybersecurity, and managing the inherent risks of AI integration. The study advocates for a balanced approach in AI adoption, emphasizing the need for robust security measures, continuous monitoring, and adapting to the evolving regulatory and technological landscape.

Knowledge graph reasoning for cyber attack detection

AbstractIn today's digital landscape, cybercriminals are constantly evolving their tactics, making it challenging for traditional cybersecurity methods to keep up. To address this issue, this study explores the potential of knowledge graph reasoning as a more adaptable and sophisticated approach to identify and counter network attacks. By leveraging graph structures imbued with human‐like thinking, this method enhances the resilience of cybersecurity systems. The study focuses on three critical aspects: data preparation, semantic foundations, and knowledge graph inference techniques. Through an in‐depth analysis of these components, the research aims to reveal how knowledge graph reasoning can improve cyberattack detection and enhance the overall efficacy of cybersecurity measures, including intrusion detection systems. The proposed approach has undergone extensive experimentation to validate its effectiveness compared to existing methods. The results of the experiment have shown a remarkable advancement in accuracy, speed, and recall for recognition, surpassing current methods. This achievement is a notable contribution in the realm of managing big data in cybersecurity. The study establishes a foundation for the automation of network attack detection, ultimately enhancing overall network security.

Organizational Cybersecurity Systems and Sustainable Business Performance of Small and Medium Enterprises (SMEs) in Saudi Arabia: The Mediating and Moderating Role of Cybersecurity Resilience and Organizational Culture

Cybersecurity challenges in Saudi Arabia’s service and manufacturing sectors are escalating due to increased digital adoption, highlighting the need for robust security measures and awareness in SMEs. Therefore, this research is significant due to the increasing reliance on digital technologies and the unique cybersecurity challenges faced by SMEs in these vital economic sectors. With rapid technological advancements, IT capabilities and cybersecurity have become paramount, particularly in the post-COVID-19 era. The service and manufacturing sectors in Saudi Arabia have seen significant shifts towards digital operations. This study aimed to explore the impact of organizational cybersecurity systems on organizational resilience and sustainable business performance in Saudi Arabia’s service and manufacturing sectors, examining the mediating and moderating effects of organizational resilience and culture. A quantitative research method was employed, combining a thorough literature review with empirical data from a sample of 394 respondents in Saudi Arabia, split evenly between the service and manufacturing sectors. Smart PLS 3.3.3 was used to test the proposed hypotheses. The findings suggested a positive effect of the factors of organizational cybersecurity systems on organizational resilience. Organizational cybersecurity systems also significantly influenced sustainable business performance; however, organizational resilience and culture did not play mediating and moderating roles. This study is one of the first to offer a nuanced analysis of IT capabilities and cybersecurity within Saudi Arabia’s service and manufacturing sectors, especially in a post-COVID-19 context. The insights gleaned contribute to the academic discourse and have pivotal managerial implications for organizations navigating the digital era in Saudi Arabia.

An Ontology-Based Cybersecurity Framework for AI-Enabled Systems and Applications

Ontologies have the potential to play an important role in the cybersecurity landscape as they are able to provide a structured and standardized way to semantically represent and organize knowledge about a domain of interest. They help in unambiguously modeling the complex relationships between various cybersecurity concepts and properties. Leveraging this knowledge, they provide a foundation for designing more intelligent and adaptive cybersecurity systems. In this work, we propose an ontology-based cybersecurity framework that extends well-known cybersecurity ontologies to specifically model and manage threats imposed on applications, systems, and services that rely on artificial intelligence (AI). More specifically, our efforts focus on documenting prevalent machine learning (ML) threats and countermeasures, including the mechanisms by which emerging attacks circumvent existing defenses as well as the arms race between them. In the ever-expanding AI threat landscape, the goal of this work is to systematically formalize a body of knowledge intended to complement existing taxonomies and threat-modeling approaches of applications empowered by AI and to facilitate their automated assessment by leveraging enhanced reasoning capabilities.

Bridging the Cybersecurity Gap: A Comprehensive Analysis of Threats to Power Systems, Water Storage, and Gas Network Industrial Control and Automation Systems

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.

Challenges arising from cyber security in the dimension of modern global security (on the example of the Russia-Ukraine war)

The challenges and threats from cyber security are increasing every day in the world. All this has a significant impact on international relations. When we are dealing with such a revolutionary development of technology as in the 21st century, it is already necessary for all states to have high-standard cyber security systems. This is not an easy issue to solve, because cyber security requires quite a lot of finances, human resources, and also specially trained professionals. Threats emanating from cyberspace need a proper response, in this case we have no choice, the whole world is facing danger. Cybercrime and the damage caused by it are increasing year by year. Also, all this affects a person psychologically and leaves a feeling of insecurity. The biggest problem is that aggressive states, terrorist organizations, non-state groups, large corporations, etc. are mostly involved in this virtual war (as in the real one). As an example, we can cite such an aggressor state as Russia, which carries out major cyber attacks against Ukraine, Georgia and other states whose cyber security systems are less protected. The transition of political, military, social or criminal processes into cyberspace has made cyber security one of the main segments of state security. Countries with developed cyber-offensive potential, primarily Russia, successfully use cyberspace both during war and conflict, as well as in peacetime, to gain geopolitical advantage. This article discusses the challenges and threats associated with the development of modern cyber and information technologies, analyzes the threats associated with the new information security capabilities of modern states, including cybersecurity. The aim of the paper is to present the role of cyber security in the Russia-Ukraine war and the threats arising from it. The following methods are used in the paper: methods of historical-descriptive, policy research and comparative analysis. The paper uses the theories of balance of power and securitization.

Technical solutions to prevent blackouts in order to provide the population with electricity: The case of Ukraine

Due to the deteriorating condition of the power grids and the increasing number of power outages, research on technical solutions to prevent blackouts in the Ukrainian energy system is becoming an extremely relevant and necessary task. This study aims to analyse technical solutions aimed at increasing the resilience of Ukraine’s energy system to prevent blackouts and ensure reliable electricity supply to the population. The methods used include the analytical method, classification method, functional method, statistical method, synthesis method, and others. The study analysed modern technical solutions to improve the resilience of the Ukrainian energy system. The study included a detailed analysis of innovative approaches to modernizing the energy infrastructure. The primary objective was to study and evaluate modern technologies for designing new power lines with improved transmission characteristics. The study emphasized the importance of expanding automation systems to effectively monitor and control the state of the power grid. The study also identified the importance of using energy storage, developing renewable energy sources and improving electricity consumption forecasting systems. Flexible load management measures and improved cybersecurity systems were identified as critical. It is noted that the implementation of the project to provide electricity to the conditional area will be a key step in improving the lives of the local population and providing the necessary conditions for the development of the area’s infrastructure and economy. In addition, the operation of generators for electricity supply will help to reduce the feeling of lack of electricity among residents and ensure reliability in the use of electricity for all sectors of the district’s economy. The overall conclusion is that the implementation of such technical solutions will significantly increase the resilience of Ukraine’s energy system. The results obtained make it possible to effectively avoid blackouts and ensure a sustainable electricity supply to the population. This allows energy companies, government agencies and other stakeholders to optimize energy resource management and make informed decisions to ensure the sustainable and efficient operation of Ukraine’s energy system in the face of a possible blackout risk

Development of methods for neutralizing «Zero-day» threats

Objective. The purpose of this study is to develop and analyze methods for neutralizing «zero-day» threats in order to increase the level of cybersecurity and protection of information systems. Method. In this article, a behavioral analysis of the threat is used. The characteristic features of the zero-day exploit behavior have been studied. The threat model is based on solving the tasks of timely detection and neutralization of the threat. Result. The actual problem of information systems security - the threat of «zero-day» is considered. The review of existing neutralization methods and discussion of effective new approaches were carried out. It has been revealed that the main vulnerability is outdated threat signatures. Threat detection is based on a study of the behavior of software a comparison with the previous day tracking is possible mainly by analyzing log files taken from an automated workplace. Conclusion. The content of this work emphasizes the importance of developing methods to neutralize «zero-day» threats in order to avoid the centralized spread of vulnerability and infection of a large number of automated workplaces, which can lead to the suspension of production processes within a large enterprise.

A Systematic Review on Security Attacks and Countermeasures in Automotive Ethernet

In the past years, the automotive industry has experienced a technological revolution driven by the increasing demand of connectivity and data to develop driver-assistance systems and autonomous vehicles, and improve the mobility experience. To provide higher bandwidth in in-vehicle communication networks, carmakers are choosing Ethernet technology, which becomes Automotive Ethernet (AE) when applied in in-vehicle communication networks. However, with the rise of vehicle connectivity, the cybersecurity of vehicle systems has become a primary concern for the automotive industry. To address this issue, we conducted a systematic review, deeply analyzing the impact of AE on security and safety, and comparing it with the current in-vehicle communication solutions like Controller Area Network protocol. We retrieved the key security attacks and mitigations proposed in the current literature to highlight their significance, including a mapping between the regulation UNECE WP.29 R155 and the retrieved answers. We found that the industry has only implemented some automotive-dedicated Ethernet solutions to date. In the near future, the vehicle and road ecosystems may require more exclusive automotive solutions to meet specific constraints such as low latency. Our results can provide a comprehensive baseline, both for industry and academia, for the current and future development of AE.