Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
4 results
Search Results
Item Restricted AI-Powered Multimodel Detection System for Cybersecurity Attacks: Design, Implementation, and Evaluation(Saudi Digital Library, 2025) Alhazmi, Marwan; Nguyen, HoangAs cyber threats have become increasingly complex, so too has the need for advanced detection methods to be able to analyze different types of data. Historically, traditional intrusion detection systems (IDS), have relied on analyzing one form of data, either a statistical analysis of network traffic or an alert log written in text format. These limitations restrict the capability of IDSs to detect the many complexities associated with modern attacks. Therefore, this dissertation proposes an AI powered, multimodel detection system that utilizes a combination of both structured network data, and unstructured alert text, to improve the performance of intrusion detection systems. The methodologies include preprocessing and feature extraction on the CICIDS2017 dataset, machine learning algorithms for the analysis of structured data and Natural Language Processing (NLP) algorithms for the analysis of text data. The multimodel fusion method used late fusion where the predictions from each modality are combined to produce a single prediction. In addition, several classification algorithms were trained and tested including Random Forest, Logistic Regression, and Text Classification. Results showed that the multimodel system significantly outperformed the single-modality systems based on the evaluation metrics of Accuracy, Precision, Recall, and F1-Score. Furthermore, the multimodel fusion strategy enhanced the context of the detection by reducing false positive detections; this addresses a major challenge that is commonly experienced by researchers in the field of Intrusion Detection Systems (IDS). Therefore, this dissertation provides a practical, scalable, multimodel AI-based framework for detecting cybersecurity threats and demonstrates the effectiveness of using a combination of structured and unstructured data sources, along with providing direction for further advancements in Intelligent Intrusion Detection Systems.34 0Item Unknown ADAPTIVE INTRUSION DETECTION SYSTEM FOR THE INTERNET OF MEDICAL THINGS (IOMT): ENHANCING SECURITY THROUGH IMPROVED MUTUAL INFORMATION FEATURE SELECTION AND META-LEARNING(Towson University, 2024-12) Alalhareth, Mousa; Hong, SungchulThe Internet of Medical Things (IoMT) has revolutionized healthcare by enabling continuous patient monitoring and diagnostics but also introduces significant cybersecurity risks. IoMT devices are vulnerable to cyber-attacks that threaten patient data and safety. To address these challenges, Intrusion Detection Systems (IDS) using machine learning algorithms have been introduced. However, the high data dimensionality in IoMT environments often leads to overfitting and reduced detection accuracy. This dissertation presents several methodologies to enhance IDS performance in IoMT. First, the Logistic Redundancy Coefficient Gradual Upweighting Mutual Information Feature Selection (LRGU-MIFS) method is introduced to balance the trade-off between relevance and redundancy, while improving redundancy estimation in cases of data sparsity. This method achieves 95% accuracy, surpassing the 92% reported in related studies. Second, a fuzzy-based self-tuning Long Short-Term Memory (LSTM) IDS model is proposed, which dynamically adjusts training epochs and uses early stopping to prevent overfitting and underfitting. This model achieves 97% accuracy, a 10% false positive rate, and a 94% detection rate, outperforming prior models that reported 95% accuracy, a 12% false positive rate, and a 93% detection rate. Finally, a performance-driven meta-learning technique for ensemble learning is introduced. This technique dynamically adjusts classifier voting weights based on factors such as accuracy, loss, and prediction confidence levels. As a result, this method achieves 98% accuracy, a 97% detection rate, and a 99% F1 score, while reducing the false positive rate to 10%, surpassing previous results of 97% accuracy, a 93% detection rate, a 97% F1 score, and an 11% false positive rate. These contributions significantly enhance IDS effectiveness in IoMT, providing stronger protection for sensitive medical data and improving the security and reliability of healthcare networks.28 0Item Unknown A Distributed and Hybrid AI-Based Security Framework for 5G Real-time Applications(Washington University in St. Louis, 2024-08-15) Ghubaish, Ali Hussain A; Chamberlain, Roger; Dutta, Ashutosh; Jain, Raj; Ottley, Alvitta; Zhang, NingThis dissertation develops a multifaceted security framework tailored for 5G-enabled real-time Internet of medical things (IoMT) systems to significantly enhance the security infrastructure within healthcare environments. The framework pivots around three core technological advancements: the development of the light feature engineering based on the mean decrease in accuracy (LEMDA), the construction of a 5G testbed that serves as a distributed intrusion detection system (IDS), and the implementation of a hybrid deep reinforcement learning (HDRL) method. LEMDA represents a breakthrough in data processing for IoMT systems. By intelligently reducing data complexity, LEMDA enhances the speed and accuracy of threat detection mechanisms, which is crucial for handling the immense volumes of data generated in healthcare settings. This method speeds up the detection process and ensures that essential data nuances are not lost, thereby maintaining high precision in threat identification. Establishing the 5G testbed introduces a novel approach to distributed IDS. This testbed leverages the latest in 5G and multi-access edge computing (MEC) technologies to distribute the processing load, thereby enhancing the overall resilience and efficiency of the network. This strategic distribution also helps overcome traditional challenges associated with centralized systems, such as scalability issues and vulnerability to single points of failure. Furthermore, this initiative has led to creating a new dataset specifically designed to support the development of IDS methodologies congruent with the architectures of 5G and MEC. This dataset is a valuable resource for researchers across both academic and industrial spheres, facilitating the advancement of tailored intrusion detection strategies. Lastly, the HDRL method integrates deep learning and reinforcement learning techniques tailored to harness network and host data for improved threat detection. This innovative approach dynamically adapts to evolving threat landscapes, reducing the need for constant human supervision and frequent retraining. The HDRL method showcases a significant enhancement in threat detection efficacy, setting new benchmarks in the field. In addition to these primary contributions, the dissertation delves into creating comprehensive datasets through the EHMS testbed and reviews current IoMT security measures and attack techniques. These endeavors provide a holistic view of the security landscape and inform the development of the proposed security framework.24 0Item Restricted Designing Intrusion Detection System Using Python(University of Portsmouth, 2024-05-03) Alzahrani, Omar; Fasunlade, OluwafemiThis project focuses on developing a Network-based Intrusion Detection System (NIDS) using Python to enhance real-time cybersecurity defences. The system aims to detect and adapt to evolving cyber threats through advanced monitoring and machine learning techniques. Key objectives include improving protocol monitoring, integrating machine learning for accurate threat detection, and implementing efficient incident logging. The literature review identifies the limitations of existing Python-based NIDS solutions. The project meticulously defines the system's requirements, emphasising real-time monitoring, anomaly detection, and scalability. The development phase uses Python to create functional classes and methods for detection tasks, incorporating advanced techniques for identifying sophisticated threats. The NIDS is validated through rigorous testing, showcasing its effectiveness against simulated attacks using a hybrid approach of signature-based and machine learning algorithms. The project's comprehensive evaluation underscores its efficiency and adaptability, contributing significantly to cybersecurity defence and laying the groundwork for future NIDS advancements.61 0