SACM - Australia
Permanent URI for this collectionhttps://drepo.sdl.edu.sa/handle/20.500.14154/9648
Browse
4 results
Search Results
Item Restricted An AI-Driven, Secure, and Trustworthy Ranking System for Blockchain-Based Wallets(University of Technology Sydney, 2024-07-08) Almadani, Mwaheb; Farookh HussainThe significance of blockchain security has gained considerable interest as blockchain technologies grow in popularity. The spectacular rise in cryptocurrency values has also increased the adoption of blockchain-based wallets(BW/BWs). This tendency emphasizes the need for comprehensive security measures to protect digital assets, maintain transaction integrity and preserve trust in the blockchain networks. The most critical concern surrounding blockchain-based wallets is managing users' private keys, which are essential for authorizing transactions and accessing the digital cryptocurrencies stored in the blockchain network. In recent years, malicious actors have increased efforts to compromise these private keys and take control of the BW's digital assets. Therefore, ensuring the security of private keys through rigorous security protocols is paramount to defend against unauthorized access and potential financial losses. This thesis aims to investigate the integration of hard security, such as authentication techniques and access controls, and soft security measures, such as trust models and ranking systems, in the context of BWs. By incorporating tangible physical defenses (hard security) with intangible procedural strategies (soft security), we present a comprehensive framework for enhancing BW solution security and trustworthiness. This is essential for the widespread adoption and use of blockchain technology in financial transactions and digital asset management. This thesis proposes a secure, intelligent, and trustworthy approach for BW solutions that incorporates 2FA and MFA as hard security measures and an AI-driven ranking system as soft security measures. We have developed a BW website (BWW) with four authentication mechanisms, including different factors such as TOTP and biometrics through facial recognition, allowing BW users to choose their preferred level of security. The BWW remarkably improves the security of BW solutions by defending them against various threats, including sophisticated cyber-attacks, unauthorized access and human-caused weaknesses. Moreover, We introduce a trust-based ranking system (TBW-RAnk) for BW solutions that transparently ranks the BW solutions according to several objective and trusted criteria. TBW-RAnk is built using three AI models, namely the random forest classifier (RFC), the support vector classifier (SVC) and deep neural network (DNN). It has two modes: general and customized for a comprehensive and accurate assessment and recommendation for BW users. Consequently, BW users can make informed decisions and increase their security within the blockchain ecosystem. The proposed approach enhances the security and trustworthiness of BWs and increases their acceptance in the market.42 0Item Restricted Towards Effective and Adaptive Anomalybased Intrusion Detection Methods for Industrial Network Systems(RMIT University, 2024-04-18) Alsaedi, Abdullah; Tari, ZahirModern Industrial Network Systems, characterised by the integration of Cyber-Physical Systems (CPSs) and the Internet of Things (IoT), are at the forefront of technological progress in Industry 4.0. They enable advanced automation, data exchange, and system monitoring on a global scale. However, these advancements also increase their vulnerability to cyber threats, particularly to targeted attacks launched by adversaries with high motivation and domain knowledge. These attacks aim to cause significant damage to the physical operation of critical infrastructures. The direct impact of these systems on physical processes means that compromises can lead to severe equipment damage, environmental disruptions, and even loss of human life. Hence, securing these systems requires advanced, robust, and adaptive cybersecurity measures. Anomaly-based Intrusion Detection Systems (IDSs) are crucial for securing IT systems but often fail to fully protect Industrial Network Systems against targeted attacks. Traditional IDSs cannot monitor the physical operations integral to these systems, making it vital to develop detection methods to oversee physical activities, as attacks may impact these operations. Current detection methods face challenges, including a lack of comprehensive benchmark datasets for modern industrial setups and difficulties adapting to the dynamic nature of industrial environments. This underscores the urgent need for research to address these significant issues. This thesis addresses the critical challenges of securing modern Industrial Network Systems, given their growing prevalence and the increasing sophistication of cyber threats. The primary aim is to develop innovative, advanced anomaly-based intrusion detection methods specifically tailored to these systems. These methods aim to identify targeted attacks that subtly alter system behaviour while evading detection. The emphasis is on real-time monitoring of multi-sensor measurements to identify threats in large-scale, evolving data streams, thus preventing significant damage to the physical infrastructure and protecting it from emerging threats. This research will tackle four significant research challenges. The first involves creating a representative benchmark dataset for evaluating intrusion detection solutions in Industrial Network Systems, addressing the lack of existing datasets that capture the specific nuances of these systems. The subsequent three challenges will focus on developing a set of effective, robust and adaptive IDS solutions. Collectively, these solutions aim to address the primary objectives of this research, thereby achieving its overall aim. First, practical evaluation of anomaly-based intrusion detection methods tailored to Industrial Network Systems hinges on the availability of datasets that accurately reflect real-world systems dynamics. Such datasets are essential for assessing the accuracy and effectiveness of security solutions. However, there is a notable lack of such datasets, which often miss critical elements like sensor measurement data. To address this, this research introduces the TON_IoT dataset, a comprehensive compilation of telemetry data, operating system logs, and network traffic designed to reflect the complexity of modern Cyber-Physical Systems (CPSs) and the Internet of Things (IoT). Unlike existing datasets, TON_IoT integrates sensor measurement data crucial for identifying sophisticated, subtle cyber threats, thus serving as an invaluable resource for the research community. It aids in understanding CPS/IoT vulnerabilities and promotes advanced intrusion detection solutions suitable for the evolving threats in Industry 4.0. Second, with the proliferation of embedded sensors in modern industrial infrastructure, these systems produce a vast volume of multi-sensor data that hold valuable insights about their operational dynamics for anomaly-based intrusion detection tasks. However, capturing these insights is challenging due to the inherent complexities, temporal intricacies, and inherent noise. Existing detection methods struggle with these issues, leading to security inefficiencies within the systems they aim to protect. Addressing this challenge, this research introduces the UnSupervised Misbehaviour Detection (USMD) method, a novel unsupervised and model-free anomaly-based intrusion detection method tailored for multi-sensor industrial data. USMD consists of a robust Unified Learner Network and a misbehaviour detector, leveraging an innovative deep learning-based method to effectively learn and represent normal system behaviour for anomaly detection. Evaluated against state-of-the-art methods, USMD demonstrates superior performance, underscoring its potential as an effective solution for securing complex and noisy industrial environments. Thirdly, modern Industrial Network Systems are dynamic environments where changes such as environmental shifts cause unpredictable variations in operational/measurement data, leading to concept drift. This drift significantly impacts the accuracy and reliability of Machine Learning (ML)-based security measures in these systems, potentially leading to diminished effectiveness in anomaly detection and response capabilities. To tackle this, this research presents ReActive concept Drift mAnagement with Robust variational inference (RADAR), a novel unsupervised framework designed explicitly for evolving and high-dimensional data streams. RADAR addresses uncertainties and temporal dependencies in measurement data, significantly improving the dynamic adaptation of ML models to changing data statistics. At the heart of RADAR lies the innovative use of two main methods: temporal discrepancy measure, and intensity-aware analyser. Collectively, these methods enable RADAR to determine the effective adaptation decision to ensure sustained accuracy and reliability of ML-based analytics and security solutions. Experiments conducted using synthetic and real-world datasets demonstrate that RADAR outperforms other benchmarks with the best F-score of 0.86 and obtains efficient runtime, offering a reactive, robust solution to manage concept drift in critical industrial operations. Lastly, the primary challenge in intrusion detection is the ability to adapt to evolving “normal” behaviour, especially in the face of concept drift. Current methods struggle with this in dynamic environments, leading to decreased sensitivity and specificity in intrusion alerts due to issues like self-poisoning and catastrophic forgetting in real-time systems. Addressing these challenges, this research introduces the Robust and adaptive Deviation detection for StreAming and Dynamic Sensor Data (RDSAD) method. RDSAD is specifically designed to overcome the challenges of concept drift, self-poisoning, and catastrophic forgetting in real-time monitoring of high-dimensional measurement data. It features two novel components: Dynamic Deviation Recognition (DDR) for accurate deviation detection, and Drift-aware Model Adaptation (DMA) for incremental updates, maintaining historical knowledge. RDSAD has shown excellent performance in anomaly detection, achieving an AUC of 0.90 and efficient runtime with large data streams, offering a robust, efficient solution for real-time anomaly detection and enhanced cybersecurity in industrial environments.34 0Item Restricted Cybersecurity Practices, Challenges and Applications in Saudi Smart Cities: Developing and Testing Extended UTAUT3 Model Using Multi-stage Samplings(Saudi Digital Library, 2023-12-04) Alhalafi, Nawaf Hamdan T; Veeraraghavan, PrakashThe Kingdom of Saudi Arabia has been making significant progress towards developing intelligent cities, with projects such as NEOM and Riyadh City. Therefore, this study investigates the challenges and factors influencing the adoption of cybersecurity practices in smart cities within the Kingdom of Saudi Arabia using the cybersecurity-based Unified Theory of Acceptance and Use of Technology (UTAUT3) framework. In four phases, the study initially collected insights from the public and IT professionals through pre-test surveys to identify key challenges in cybersecurity adoption. The study then conducted a second survey to refine the UTAUT3 model in line with the unique cybersecurity challenges experienced in smart Saudi cities. This allowed exploring the economic, social, and cultural factors affecting cybersecurity implementation. Economic factors included privacy design and cyber threat intelligence; social factors covered digital trust and resilience; and cultural factors focused on cybersecurity competency and awareness. In the third phase, the study validated the extended UTAUT3 model, assessing the suitability of data for analysis and evaluating the reliability and validity of the measurement constructs. The aim was to enhance understanding of the factors impacting cybersecurity adoption, ensuring that the extended model is useful for future research and policy development. In the final phase, post-testing was conducted to measure behavioural intentions in adopting cybersecurity practices. Results showed that factors such as performance expectancy, effort expectancy, social influence, facilitating condition, and various attributes of cybersecurity (resilience, safety, confidentiality, availability, and integrity) positively influence the behavioural intention to adopt cybersecurity. Multi-group analysis revealed differences between IT professionals and the general public in the behavioural intention of adopting cybersecurity in smart cities. This study contributes significantly to understanding cybersecurity adoption in smart cities, providing valuable insights for future interventions or policies. It underscores the need to consider group differences when promoting cybersecurity adoption to ensure effective outcomes.63 0Item Restricted Understanding Cybersecurity Behaviour and Attitudes of Young Adults in Saudi Arabia(Saudi Digital Library, 2023-11-14) Alanazi, Marfua; Tootell, Holly; Freeman, MarkAs the use of the Internet for personal and business purposes continues to grow exponentially, cybersecurity has become a global issue for individuals as well as governments and organisations, who face increasing risks in their online activities. The Kingdom of Saudi Arabia (KSA), for instance, has been a target of persistent cyberattacks that threaten its economic and social well-being. Indeed, it has the highest level of cyber risk among all Middle Eastern countries. Young adults in KSA are particularly vulnerable to cyber threats as their engagement with the Internet expands rapidly. Yet the cybersecurity behaviour (CSB) of young people, especially those in late-adopting countries like KSA, remains an under-researched topic. This thesis addresses this gap in knowledge. It adopted a socio-behavioural perspective, with particular focus on better understanding the intrinsic and sociodemographic factors that influence the engagement in safe online practices of young adults in KSA. To this end, it developed an original theoretical model based on the main constructs of the theory of planned behaviour (TPB), combined with the additional factors of perceived awareness and knowledge of cyber threats. The demographic characteristics examined were gender, age, type of residence, educational history, information technology (IT) experience, previous training, and level of IT professionalism. Most previous cybersecurity studies have relied on quantitative data collected via survey methodology, a researcher-directed approach that limits our ability to understand the perspectives of users themselves. Accordingly, the present study adopted a mixed-methods design and used an online questionnaire to collect both quantitative and qualitative data from a random sample of 1,581 young Saudi college students aged 18-30. The quantitative data were analysed using least-squares partial structural equation modelling (SEM). The results indicated that attitude (ATT), subjective norms (SN), and perceived behavioural control (PBC) strongly influenced young adults’ intentions to practise positive CBT (IPC), and that three factors—KCT, ATT, and SK—were predictors of young adults’ perceived awareness of cyber threat (PACT). In addition, PACT was found to play a significant role in young adults’ CSB by positively influencing their IPC. Both PACT and IPC were identified as the direct determinants of practising positive CSB, but PBC was not. In relation to sociodemographic factors, the results suggested that young men were more likely than young women to practise positive online CSB. There was also a direct relationship between increasing age and good CSB practices. Multi-group analysis was used to investigate moderating effects and assess the interactions among the factors considered. Of the potential mediators, only gender and type of residence were found to have no effect on CSB across socio-demographic divisions, while factors related to the IT-educational field, IT-related work experience and training, and professionalism in IT were shown to strongly influence the behaviour of young adults. The survey instrument included two open-ended items to collect qualitative data. These asked participants about the most prominent cyber threats encountered by young Saudi adults and the most common practices they adopted to protect themselves online. Although 1,581 students completed the questionnaire, only 621 usable responses were obtained for these items. Analysis of the qualitative data indicated that most respondents were aware of cyber-threats online associated with use of online social networks, accounts and digital cards, online communication and interaction, e-mail, web/internet access, and personal e-devices, but not access to online services, online privacy policies, or access control – passwords. The results also suggested that most participants were aware of good online security behaviours regarding securing and regularly updating personal passwords, ensuring secure use of email, using antivirus software, and never sharing personal data with unreliable parties online, but not complying with safe online use policies or ensuring secure online data storage. Overall, the results provide previously unavailable information on young Saudi adults’ online CSB and the factors that influence their motivation to engage in positive CSB. The qualitative results, in particular, contribute to a more in-depth understanding of the prominent cyber threats that young adults encounter online, as well as the most common practices that they adopt to protect themselves. The findings have important implications for the development of policies, strategies and education and training programs to improve cybersecurity awareness among young people and protect them from the risks of cyber threats in schools, universities, and professional spaces in KSA and other late-adopting, developing countries. In particular, they highlight the importance of adopting a socio-behavioural perspective in future research.37 0