Saudi Cultural Missions Theses & Dissertations
Permanent URI for this communityhttps://drepo.sdl.edu.sa/handle/20.500.14154/10
Browse
6 results
Search Results
Item Restricted A MULTI-LAYER DEFENSE FRAMEWORK FOR ENHANCING ADVERSARIAL ROBUSTNESS OF MACHINE LEARNING-BASED INTRUSION DETECTION SYSTEMS(Saudi Digital Library, 2026) alshmmri, Eiman Salem; Almatarneh, Rami JibreelThe rapid evolution and increasing sophistication of cyber threats, especially the adversary attacks have revealed significant weaknesses in the traditional Intrusion Detection Systems (IDS). The traditional signature-based systems can no longer identify a zero-day attack or respond to an ever-changing pattern of threats. Even though the Intrusion Detection Systems based on Machine Learning (ML-IDS) have enhanced detection performance, most of the existing systems are not robust in the adversarial settings and are commonly tested at fixed and static settings. This restricts the knowledge of model resilience, stability and generalization in real and unstable cybersecurity conditions. This thesis will solve those issues by introducing a single, configuration-sensitive assessment system of ML-based intrusion detectors. The framework combines tree models, such as Random Forest, Extra Trees, and XGBoost, and an optimized ensemble method to improve predictive performance, stability, and generalization. It also includes feature selection as a way of minimizing redundancy and enhancing efficiency and class imbalance management as a way of stabilizing learning when the data distribution is skewed. Moreover, the adversarial perturbation testing is done both in white-box and black-box to represent real-life attack conditions. A multi-level defense mechanism is also implemented to enhance model resilience and reduce the effect of adversarial attack. The framework is tested on two non-homogeneous benchmark datasets, namely the CIC-IDS2018, published in 2018, and the updated release of the ToN-IoT dataset, update published in 2025. It allows assessment in various time frames and changing threat patterns, so that the offered approach will be highly efficient in both well-established and recently re-evaluated data sets. The experimental results demonstrate that the proposed framework achieves a high level of performance, with accuracy exceeding 95% in many cases, alongside strong F1- score and AUC values across different attack categories. The ensemble model exhibits enhanced stability and generalization capability, while feature selection and class imbalance handling contribute significantly to improving efficiency and robustness. Moreover, the proposed defense mechanism effectively reduces performance degradation in adversarial environments and enhances system recovery. These findings highlight the effectiveness of the proposed framework in developing robust, adaptive, and resilient Intrusion Detection Systems capable of maintaining high performance under diverse and evolving cybersecurity conditions.5 0Item Restricted Machine Learning Algorithms for Secure and Reliable Electric Grid Operations and Control(Saudi Digital Library, 2026-09) Bahwal, Obai; Sankar, LalithaThis dissertation develops Machine Learning (ML) algorithms for secure and reliable electric grid operations and control by addressing three related problems. The first part studies real-time event identification using synchrophasor measurements, physics-based modal decomposition, and interpretable classifiers to distinguish generation loss from load loss events. Targeted adversarial attacks are developed to evaluate robustness under both white box and gray box settings, showing that learned event identification models are susceptible to adversarial attacks and that simpler models such as logistic regression are generally more vulnerable than gradient boosting. The second part builds on this vulnerability analysis and focuses on enhancing the security of ML event identification models in a white box adversarial setting. Two mitigation strategies are developed: robust classification through iterative adversarial retraining, and a dual-classifier architecture that combines event classification with attack detection. Numerical results on the synthetic South Carolina 500-bus system show that while robust retraining provides only modest improvement, the dual classifier approach is highly effective, reducing successful undetected attacks to under 0.1%. The third part addresses reliable grid control through a forecast-integrated rolling-horizon Model Predictive Control (MPC) framework for net-demand balancing using Distributed Energy Resource Aggregators (DERAs). Each DERA is modeled as a generalized battery with state-of-charge, power, and ramping constraints, while Linear Regression (LR) and Long Short-TermMemory (LSTM) forecasting models are integrated with MPC to generate real-time allocation policies. Using high-resolution California Independent System Operator (CAISO) net-demand data, results show close tracking of net-demand and reveal clear tradeoffs among forecast horizon, update frequency, and control performance, with LSTM generally benefiting longer time-shifts and LR remaining competitive for shorter update intervals. These three parts show that effective ML for power systems must be accurate, physically grounded, cyber-resilient, and compatible with real-time operational constraints.17 0Item Restricted The Role of Artificial Intelligence in Strengthening Cyber Defense Mechanisms: Opportunities and Challenges(University of Bedfordshire, 2024) Alanazi, Mohammed; Garner, LeeThis study explores the role of Artificial Intelligence (AI) in strengthening cyber defense mechanisms, focusing on the opportunities and challenges it presents. In recent years, AI has shown potential in enhancing threat detection, response efficiency, and proactive cybersecurity measures. The study examines various AI applications in cyber defense, including machine learning for real-time threat identification and natural language processing for analyzing large-scale data patterns. While AI provides significant advantages in mitigating cyber threats, challenges such as model interpretability, ethical concerns, and vulnerability to adversarial attacks persist. The findings contribute to cybersecurity by highlighting both the promising capabilities and limitations of AI in this domain, suggesting future research directions to address these challenges.56 0Item Restricted Evaluation and Detection of Adversarial Attacks in ML-based NIDS(Newcastle University, 2024) Alatwi, Huda Ali O; Morisset, CharlesA Network Intrusion Detection System (NIDS) monitors network traffic to detect unauthorized access and potential security breaches. A Machine Learning (ML)-based NIDS is a security mechanism that uses ML algorithms to automatically detect and identify suspicious activities or potential threats in a network by analyzing traffic patterns, distinguishing between normal and malicious behaviors, and alerting or blocking unauthorized access. Despite high accuracy, ML-based NIDS are vulnerable to adversarial attacks, where attackers modify malicious traffic to evade detection and transfer these tactics across various systems. To the best of our knowledge, several crucial research gaps persist in this area that have not yet been addressed. First, there are no systematic threat models for identifying and analyzing potential threats and vulnerabilities in ML-based NIDS. This lack of structured threat modeling hinders the development of comprehensive defense strategies and leave these systems vulnerable to adversarial attacks that exploit unknown weaknesses in the ML algorithms or system architecture. The current literature employs generic adversarial attacks mainly designed for image recognition domain to assess the resilience of ML-based, but no research has verified the realism and compliance of these attacks with network domain constraints. Investigating whether these attacks produce valid network is crucial to determine their real-world threat level and the suitability of ML-based NIDS for deployment. Another gap in the literature is the lack of comprehensive evaluations that include a wide range of models, attack types, and defense strategies using contemporary network traffic data. This gap makes it difficult to verify the generalizability and applicability of the findings for real-world. The absence of standardized metrics further hampers the ability to evaluate and compare the resilience of ML-based NIDS to adversarial attacks. Finally, there is no a lightweight solution that effectively detects and classifies adversarial traffic with scoring high accuracy on both clean and perturbed data with proven efficiency over recent dataset and across various attack types and defenses. These gaps hinder the robustness of ML-based NIDS against adversarial attacks. Therefore, this Ph.D. thesis aims to address these vulnerabilities to enhance the ML-based NIDS resilience. The overall contributions include; 1) A threat modeling for ML-based NIDS using STRIDE and Attack Tree methodologies; 2) An investigation of the realism and performance of generic adversarial attacks against DL-based NIDS; 3) A comprehensive evaluation for adversarial attacks' performance consistency, models' resilience, and defenses' effectiveness; 4) Adversarial-Resilient NIDS, a framework for detecting and classifying adversarial attacks against ML-based NIDS.44 0Item Restricted EXPLORING THE TRANSFERABILITY OF ADVERSARIAL EXAMPLES IN NATURAL LANGUAGE PROCESSING(Texas A&M University-Kingsville, 2024-06-21) Allahyani, Samah; Nijim, MaisIn recent years, there has been a growing concern about the vulnerability of machine learning models, particularly in the field of natural language processing (NLP). Many tasks in natural language processing, such as text classification, machine translation, and question answering, are at risk of adversarial attacks where maliciously crafted inputs can cause them to make incorrect predictions or classifications. Adversarial examples created on one model can also fool another model. The transferability of adversarial has also garnered significant attention as it is a crucial property for facilitating black-box attacks. In our comprehensive research, we employed an array of widely used NLP models for sentiment analysis and text classification tasks. We first generated adversarial examples for a set of source models, using five state-of-the-art attack methods. We then evaluated the transferability of these adversarial examples by testing their effectiveness on different target models, to explore the main factors such as model architecture, dataset characteristics and the perturbation techniques impacting transferability. Moreover, we extended our investigation by delving into transferability-enhancing techniques. We assisted two transferability-enhancing methods and leveraged the power of Large Language Models (LLM) to generate natural adversarial examples that show a moderate transferability across different NLP architecture. Through our research, we aim to provide insights into the transferability of adversarial examples in NLP, and shed light on the factors that contribute to their transferability. This knowledge can then be used to develop more robust, and resilient, NLP models that are less susceptible to adversarial attacks; ultimately, enhancing the security and reliability of these systems in various applications.21 0Item Restricted DETECTING MANIPULATED AND ADVERSARIAL IMAGES: A COMPREHENSIVE STUDY OF REAL-WORLD APPLICATIONS(UCF STARS, 2023-11-06) Alkhowaiter, Mohammed; Zou, CliffThe great advance of communication technology comes with a rapid increase of disinformation in many kinds and shapes; manipulated images are one of the primary examples of disinformation that can affect many users. Such activity can severely impact public behavior, attitude, and be- lief or sway the viewers’ perception in any malicious or benign direction. Additionally, adversarial attacks targeting deep learning models pose a severe risk to computer vision applications. This dissertation explores ways of detecting and resisting manipulated or adversarial attack images. The first contribution evaluates perceptual hashing (pHash) algorithms for detecting image manipulation on social media platforms like Facebook and Twitter. The study demonstrates the differences in image processing between the two platforms and proposes a new approach to find the optimal detection threshold for each algorithm. The next contribution develops a new pHash authentication to detect fake imagery on social media networks, using a self-supervised learning framework and contrastive loss. In addition, a fake image sample generator is developed to cover three major image manipulating operations (copy-move, splicing, removal). The proposed authentication technique outperforms the state-of-the-art pHash methods. The third contribution addresses the challenges of adversarial attacks to deep learning models. A new adversarial-aware deep learning system is proposed using a classical machine learning model as the secondary verification system to complement the primary deep learning model in image classification. The proposed approach outperforms current state-of-the-art adversarial defense systems. Finally, the fourth contribution fuses big data from Extra-Military resources to support military decision-making. The study pro- poses a workflow, reviews data availability, security, privacy, and integrity challenges, and suggests solutions. A demonstration of the proposed image authentication is introduced to prevent wrong decisions and increase integrity. Overall, the dissertation provides practical solutions for detect- ing manipulated and adversarial attack images and integrates our proposed solutions in supporting military decision-making workflow.34 0