Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
32 results
Search Results
Item Restricted Learning Based Ethereum Phishing Detection: Evaluation, Robustness, and Improvement(University of Central Florida, 2025) Alghuried, Ahod; Mohaisen, DavidPhishing attacks continue to pose a significant threat to the Ethereum ecosystem, accounting for a major share of Ethereum-related cybercrimes. To enhance the detection of such fraudulent transactions, this dissertation develops a comprehensive framework for machine learning-based phishing detection in Ethereum transactions. The framework addresses critical aspects such as feature selection, class imbalance, model robustness, and the vulnerability of detection models to adversarial attacks. By systematically evaluating these key practices, this work contributes to the development of more effective detection methods. The first part of the dissertation assesses the current state of phishing detection methods, identifying gaps in feature selection, dataset composition, and model optimization. We propose a systematic framework that evaluates these factors, providing a foundation for improving the overall performance and reliability of detection models. The second part explores the vulnerability of machine learning models, including Random Forest, Decision Tree, and K-Nearest Neighbors, to single-feature adversarial attacks. Through extensive experimentation, we analyze the impact of various adversarial strategies on model performance and uncover alarming weaknesses in existing models. However, the varied effects of these attacks across different algorithms present opportunities for mitigation through adversarial training and improved feature selection. Finally, the dissertation investigates how phishing detection models generalize across datasets, focusing on the role of preprocessing techniques such as feature engineering and class balancing. Our findings show that optimizing these techniques enhances model accuracy and robustness, making detection methods more adaptable to evolving threats. Overall, this work presents a comprehensive framework that addresses the critical elements of phishing detection in Ethereum transactions, offering valuable insights for the development of more robust and generalizable machine learning-based security models. The proposed framework has broad implications for improving blockchain security and advancing the field of phishing detection.11 0Item Restricted Detecting abuse of cloud and public legitimate services as command and control infrastructure using machine learning(Cardiff University, 2024) Al lelah, Turki; Theodorakopoulos, GeorgeThe widespread adoption of Cloud and Public Legitimate Services (CPLS) has inadvertently created new opportunities for cybercriminals to establish hidden and robust command-and-control (C&C) communication infrastructure. This abuse represents a major cybersecurity risk, as it allows malicious traffic to seamlessly disguise itself within normal network activities. Traditional detection systems are proving inadequate in accurately identifying such abuses. Therefore, this thesis is motivated by emphasizing the urgent need for more advanced detection techniques that are capable of identifying the C&C activity hidden within legitimate CPLS traffic. To assess the extent of the cyber threat of abusing CPLS, this thesis presents an ex- tensive Systematic Literature Review (SLR) encompassing academic and industry lit- erature. The review provides a comprehensive categorization of the attack techniques utilized to abuse CPLS as C&C infrastructure. The open problems uncovered through the SLR motivate this thesis to propose a novel Detection System (DS) capable of identifying malware that abuse CPLS as C&C communication channels. Furthermore, to evaluate our system robustness against attempts to evade detection, this thesis intro- duces the Replace Misclassified Parameter (RMCP) adversarial attack. The proposed detection system leverages Artificial Intelligence (AI) techniques, combining static and dynamic malware analysis methods to accurately identify CPLS abuse. The effective- ness of the proposed system is validated through extensive experiments, demonstrating its ability to detect novel and sophisticated attacks that evade traditional security measures. The outcomes of this thesis have significant implications for enhancing the security of cloud environments, contributing valuable knowledge and practical solutions to the field of cloud security.26 0Item Restricted Disinformation Classification Using Transformer based Machine Learning(Howard University, 2024) alshaqi, Mohammed Al; Rawat, Danda BThe proliferation of false information via social media has become an increasingly pressing problem. Digital means of communication and social media platforms facilitate the rapid spread of disinformation, which calls for the development of advanced techniques for identifying incorrect information. This dissertation endeavors to devise effective multimodal techniques for identifying fraudulent news, considering the noteworthy influence that deceptive stories have on society. The study proposes and evaluates multiple approaches, starting with a transformer-based model that uses word embeddings for accurate text classification. This model significantly outperforms baseline methods such as hybrid CNN and RNN, achieving higher accuracy. The dissertation also introduces a novel BERT-powered multimodal approach to fake news detection, combining textual data with extracted text from images to improve accuracy. By lever aging the strengths of the BERT-base-uncased model for text processing and integrating it with image text extraction via OCR, this approach calculates a confidence score indicating the likeli hood of news being real or fake. Rigorous training and evaluation show significant improvements in performance compared to state-of-the-art methods. Furthermore, the study explores the complexities of multimodal fake news detection, integrat ing text, images, and videos into a unified framework. By employing BERT for textual analysis and CNN for visual data, the multimodal approach demonstrates superior performance over traditional models in handling multiple media formats. Comprehensive evaluations using datasets such as ISOT and MediaEval 2016 confirm the robustness and adaptability of these methods in combating the spread of fake news. This dissertation contributes valuable insights to fake news detection, highlighting the effec tiveness of transformer-based models, emotion-aware classifiers, and multimodal frameworks. The findings provide robust solutions for detecting misinformation across diverse platforms and data types, offering a path forward for future research in this critical area.33 0Item Restricted HYBRID MACHINE LEARNING APPROACHES FOR SOC AND RUL ESTIMATION IN BATTERY MANAGEMENT SYSTEMS(Oakland University, 2024) Hawsawi, Tarik Abdullah; Zohdy, MohamedWith the fast development of electric vehicles (EVs), new technologies are needed to manage batteries more efficiently to optimize performance and more profound and longer battery use. A significant problem that must be solved successfully is accurate estimation of the State-of-Charge (SoC) to avoid fully discharging a battery. It shortens battery life and prolongs the time it takes to charge the battery. This dissertation introduces a new approach that uses Edge Computing and real-time predictive analytics to assess the status of EV batteries and send alerts when necessary, thus facilitating energy efficiency. The Edge Impulse platform is used to predict the Remain Useable Life RUL of batteries with enhanced accuracy using EON-Tuner and DSP processing blocks, enhancing computational capability and making it feasible for edge devices. Since traditional SoC estimations include tools like Kalman filters and Extended Kalman filters, which are effective but have a considerable drawback in estimating the SoC with changing battery parameters, this study proposes a multi-variable optimization method. The method enhances performance prediction after key parameters are iteratively adjusted, thus resolving the emergence hypotheses of most existing techniques. The system was designed and tested on Jupyter Notebook, and performance indicators of accuracy, MSE, and efficiency further validated the design. This study helps ensure proper energy use and long battery life for e-vehicles, which promotes clean energy use.7 0Item Restricted Facial Emotion Recognition via Label Distribution Learning and Customized Convolutional Layers(The University of Warwick, 2024-11) Almowallad, Abeer; Sanchez, VictorThis thesis attempts to investigate the task of recognizing human emotions from facial expressions in images, a topic that has been interest of to researchers in computer vision and machine learning. It addresses the challenge of deciphering a mixture of six basic emotions—happiness, sadness, anger, fear, surprise, and disgust—each presented with distinct intensities. This thesis introduces three Label Distribution Learning (LDL) frameworks to tackle this. Previous studies have dealt with this challenge by using LDL and focusing on optimizing a conditional probability function that attempts to reduce the relative entropy of the predicted distribution with respect to the target distribution, which leads to a lack of generality of the model. First, we propose a deep learning framework for LDL, utilizing convolutional neural network (CNN) features to broaden the model’s generalization capabilities. Named EDL-LBCNN, this framework integrates a Local Binary Convolutional (LBC) layer to refine the texture information extracted from CNNs, targeting a more precise emotion recognition. Secondly, we propose VCNN-ELDL framework, which employs an innovative Visibility Convolutional Layer (VCL). The VCL is engineered to maintain the advantages of traditional convolutional (Conv) layers for feature extraction, while also reducing the number of learnable parameters and enhancing the capture of crucial texture features from facial images. Furthermore, this research presents a novel Transformer architecture, the Visibility Convolutional Vision Transformer (VCLvT), incorporating Depth-Wise Visibility Convolutional Layers (DepthVCL) to bolster spatial feature extraction. This novel approach yields promising outcomes, particularly on limited datasets, showcasing its capacity to meet or exceed state-of-the-art performance across different dataset sizes. Through these advancements, the thesis significantly contributes to the advancement of facial emotion recognition, presenting robust, scalable models adept at interpreting the complex nuances of human emotions.17 0Item Restricted The Application of IoT in Predictive Maintenance for Railway Systems: A Systematic Literature Review(University of Nottingham, 2024-09) Alghefari, Abdulrahman; Chesney, ThomasThis research explores the implementation of IoT-based predictive maintenance within railway systems, focusing on the technologies, cost implications, reliability, safety, and barriers identified in the literature. The study systematically reviews 30 peer-reviewed journals to assess the current state of IoT applications in the railway sector. Critical IoT technologies such as sensors, wireless sensor systems, and edge processing are examined in their role in enhancing predictive maintenance practices. The research highlights significant long-term cost savings associated with IoT adoption, despite high initial implementation costs. Furthermore, the study evaluates how IoT technologies contribute to improved reliability and safety by enabling real-time monitoring and predictive analysis. However, several barriers to widespread adoption are identified, including technical integration challenges, financial constraints, regulatory hurdles, and organisational resistance. The findings underscore the need for a strategic approach that will help tackle all obstacles by realising the benefits of IoT-predictive maintenance in the railway sector. This study offers significant insights for stakeholders, offering a deep understanding of the challenges of IoT-based predictive maintenance in railways. Future research directions are suggested, emphasising the importance of long-term studies, holistic approaches, and the integration of emerging technologies to address the identified barriers.16 0Item Restricted Explaining Machine Learning Classifiers For Android Malware Detection(King's College London, 2024-08-03) Bin Hazzaa, Zaid; Pierazzi, FabioThe prevalence of Android malware continues to rise, and traditional approaches are proving ineffective against the evolving tactics of direct attacks. Manually inspecting applications is no longer a practical solution. Machine learning has demonstrated success in various domains, and its high performance in Android malware detection positions it to be effectively deployed in real-world scenarios. However, real-world results have yet to align with experimental findings, and the unique requirements of the security field have led to a lack of trust in its practical application. This research aims to address this issue by utilizing best practices for conducting experiments to eliminate experimental bias and employing explanation methods to enhance the transparency and robustness of the classifier. These measures are critical for building trust among security experts, with transparent, learning-based malware detection being a paramount necessity in the security system. Providing thorough explanations is key to informed decision- making. The research utilizes activities, services and receivers feature sets from Drebin feature extraction to explore the significance of feature sets and employs explanation methods to gain deeper insights into the model.13 0Item Restricted The Complexity of The System & Decisions Through A Digital Participatory Approach(UCL, 2024-07) Khayat, Abdulaziz; Philippe, MorelThis report explores the potential of using computational tools to reinterpret the legal text of the city and trace its impact. It discusses the laws, regulations, and decision-making processes to construct cities drifting away from bureaucratic arbitrary existing city governance and decision-making models. To develop such a system for governing and making urban decisions in cities, first, we must understand the nature of cities. Analyzing the city will shed light on the complexity of its components and its nature being a multi-faceted organism. Hence, the first section contains literature reviews of prominent works of major architectural figures to uncover the bureaucratic narrative of architecture. In the second section, multiple approaches to understanding cities are discussed. The third section explores the computational potential of participatory planning. The fourth section explores the concept of text similarity in machine learning and the urban environment. Finally, the last section demonstrates the application of the discussed tools and concepts.7 0Item Restricted Evaluation of Use of Artificial Intelligence (AI) and Machine Learning to Practice and Master Colonoscopic Skills.(University of Dundee, 2024-08) Alshahrani, Norah Abdullah; Tang, BenjieAbstract Objective The abstract concisely summarizes the research project "Evaluation of Use of Artificial Intelligence (AI) and Machine Learning to Practice and Master Colonoscopic Skills." It outlines the background of flexible colonoscopy, highlighting its importance in diagnosing and treating colorectal diseases. The study emphasizes the potential of VR simulators to provide a safe, controlled training environment. It identifies the need for quantitative data defining the number of procedures required to achieve competence in VR training. The research aims to demonstrate the effect of the use of AI and machine learning in colonoscopy traning.by conducting experiments with novice subjects and collecting and analyzing data. The expected outcome is to provide quantified evidence supporting the use of VR and AI in colonoscopy training, ultimately improving training methods and enhancing patient safety. Methods The methodology of this study involves a mixed approach where novice subjects undergo hands-on training on VR colonoscopy systems. Participants are selected based on specific criteria, and consent is obtained before involvement. The study utilises a VR simulator alongside physical phantom models to ensure comprehensive training. Detailed experimental procedures are followed, including simulation-based training sessions and performance assessments. Data is collected systematically through observation, performance metrics, and feedback and analysed using statistical methods such as SPSS to quantify the proficiency-gain curve and evaluate the effectiveness of VR training in mastering colonoscopic skills. Results This study included colonoscopy examinations performed on eight volunteers four times and compared with four experts who were examined 500 times. The results indicated that the average time taken to complete the procedure varied between (5:03 to 13:10 minutes) and the time to reach the cecum (4:58 to 10:10 minutes), with statistically significant differences between volunteers (P = 0.03) in the time to reach the cecum. The comparison between the expert group and volunteers also showed statistically significant differences between experts and volunteers in some aspects, such as the time taken to reach the cecum (2:22 minutes for experts versus 7:37 minutes for volunteers). Although the percentage of time in which a clear vision was maintained was higher among experts (96.75%) compared to volunteers (92.62%), this percentage among volunteers was also statistically significant, reflecting the importance of training and practice in improving this skill. Conclusion The conclusion of this study indicates that using VR simulators and AI in colonoscopy training significantly enhances skill acquisition, reduces the proficiency-gain curve, and ensures a safer training environment. The data analysis shows a marked improvement in performance among novice subjects trained with VR, validating the effectiveness of this approach. The study provides quantified evidence supporting the integration of VR and AI technologies in medical training programs, suggesting that such methods effective.9 0Item Restricted Diagnosis of Oral and maxillofacial cysts using artificial intelligence: a literature review(University of Manchester, 2024) Almohawis, Alhaitham; Yong, SinAbstract Oral and maxillofacial cysts are cavities that can pose significant risks if not detected and treated promptly. Many of these cysts are asymptomatic, often going unnoticed until complications arise. The introduction of artificial intelligence (AI) presents a promising opportunity for early detection and management of these cysts. Aim: To explore current studies on the use of artificial intelligence in diagnosing oral and maxillofacial cysts. Objectives: To examine the existing literature in this field, assess the accuracy, effectiveness, and limitations of AI models, and identify challenges in implementing AI in clinical practice. Methods: This literature review followed a systematic approach, identifying 223 studies from PUBMED and SCOPUS databases between 1975 and 2024. After applying inclusion and exclusion criteria, 26 retrospective cohort studies were included in the final analysis. A risk of bias assessment was conducted using the ROBINS I tool. Results: The investigation revealed that AI models consistently demonstrate high accuracy in detecting oral cysts in both radiographs and digital histopathology. The ROBINS I tool indicated a moderate risk of bias in most of the included studies. Notable limitations include limited datasets, variable data quality, and a lack of explainability in AI models results. Conclusion: AI models have shown considerable effectiveness and speed in detecting both simple and complex cysts. However, to fully leverage AI's potential in clinical settings, further rigorous studies are needed to evaluate its risks, benefits, and feasibility, ensuring compliance with governmental health regulations on AI.13 0