http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/53 Cyber Security Science Tue, 16 Jun 2026 15:52:02 GMT 2026-06-16T15:52:02Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30912 Title: Systematic Literature Review of Intrusion Detection and Classification in Edge Computing: Types, Challenges, Solutions, Limitations and Research Directions Authors: Ojeniyi, Joseph Adebayo; Kigbu, Peter A.; Ahmad, Suleiman; Isah, Abdulkadir O.; Noel, Moses Dogonyaro; Subairu, Sikiru O. Abstract: This study presents a systematic literature review of intrusion detection and classification method for edge computing environment. Following PRISMA guided procedure, appropriate studies were identified from 2019 to 2026 through structured search method across relevant digital libraries, followed by thorough inclusion and exclusion screening. This review covered intrusion detection system (IDS) types and deployment structure. It also examined machine learning and deep learning method, feature engineering method, dataset, performance measures, and implementation. The review shows that host-based and anomaly-based intrusion detection system (IDS) lead in edge deployment. They track behaviors in detail and use few computing resources. Lightweight machine learning model like decision trees, random forests, and ensemble classifier are widely adopted, while Deep learning model often run into problems from limited resources. The review draws on this result to highlight key research gaps. It suggests paths ahead that focus on lightweight and federated detection system, standard test dataset, and low resource adaptive learning. It serves as a full guide for researchers and practitioners. Aim to build strong, scalable, and smart intrusion detection systems for safe edge computing environment. Description: N/A Sun, 01 Mar 2026 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30912 2026-03-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30911 Title: Machine Learning-Driven Cybersecurity Solutions for Enhanced Smart Grids and Critical Infrastructure: A Review Authors: Idowu, Afe; Ismaila, Idris; Ojeniyi, Joseph Adebayo; Subairu, Sikiru O.; Noel, Moses Dogonyaro Abstract: Distributed Denial of Service (DDoS) attacks have emerged as one of the most pervasive and damaging threats to network security, disrupting services and incurring substantial financial costs. Machine learning (ML) has been widely explored as a potential solution to enhance DDoS detection and mitigation. This systematic review evaluates the effectiveness of ML techniques in detecting DDoS attacks, synthesizing findings from studies published between 2004 and 2024. The review analyzes models such as Random Forest, Support Vector Machines (SVM), and K-Nearest Neighbors (K-NN) based on key performance metrics like accuracy, precision, recall, and F1-score. A comprehensive search of multiple databases, including Web of Science, IEEE, Scopus, ScienceDirect, and Google Scholar, resulted in 19 studies that met inclusion criteria. The findings show that ensemble methods, particularly Random Forest, consistently outperformed other models in terms of detection rates, mainly due to their ability to handle large feature sets and reduce overfitting. Support Vector Machines also performed well in specific scenarios. However, their effectiveness was sometimes limited by computational complexity and the dataset size. K-Nearest Neighbors showed mixed results, depending on the nature of the attack patterns. This review emphasizes the potential of ensemble learning approaches for DDoS detection, demonstrating their robustness in dynamic environments. The review identifies key gaps in the existing research, including the need for better feature selection and exploring deep learning techniques to enhance DDoS detection accuracy and adaptability further. This study contributes valuable insights into the strengths and limitations of ML-based DDoS detection models, offering a foundation for future advancements in the field. It underscores the importance of continued research into hybrid and deep learning models to address the evolving and increasingly sophisticated nature of DDoS attacks in real-world applications. Description: N/A Tue, 08 Jul 2025 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30911 2025-07-08T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30909 Title: Homomorphic Encryption Scheme Parties, Platforms, Techniques, Complexities, Limitations and Future Directions: A Systematic Review Authors: Mamza, Joshua E.; Ismaila, Idris; Ojeniyi, Joseph Adebayo; Abdulhamid, Shafii M.; Noel, Moses Dogonyaro; Ahmad, Suleiman Abstract: Homomorphic Encryption (HE) is a cryptographic encryption technique that allows computational functions being carried out on encrypted data with the view of maintaining the functional properties of the data that is encrypted. The outcome is that the computation performed on the encrypted data remain the same as the decrypted data. Homomorphic Encryption revolved around privacy enhancing technology which react to the challenges of data sharing in an organization such as Personal Identifiable Information, Health Care Information, and Financial Transaction Data. All these data require privacy which is a prevalent issue. Significant achievement and advancement has been achieved in the design, development and implementation of HE techniques, thereby enhancing their efficiency and its practical applicability. This study would explore the parties, platforms, techniques, complexities and limitations associated with HE Schemes. Articles written in English, published in peer-reviewed academic journals, and released between 2020 and 2025 met the inclusion criteria. In the end, this study examined 40 relevant articles in total. The review delves into the most recent advancement in HE techniques, complexities and limitations. Also, focus is given to the roles and responsibilities of various stakeholders, platforms and challenges encountered in real world application. Our key finding indicates that while HE offers important privacy benefits on applications, its deployment may be hindered by massive computational and communication overheads. This study clarifies the potential of HE in addressing the challenges in data privacy and security as it is applied in real-world situations such as cloud computing environments and federated learning while maintaining its computation feasibility. Description: N/A Sun, 01 Mar 2026 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30909 2026-03-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30908 Title: BAYESIAN-OPTIMIZED ENSEMBLE SUPPORT VECTOR MACHINE MODEL FOR PHISHING EMAIL DETECTION Authors: Aji, Igba I.; Ismaila, Idris; Subairu, Sikiru O.; Noel, Moses Dogonyaro; Ahmad, Suleiman Abstract: With the rapid growth of email use, phishing and malware attacks have become more frequent and sophisticated, often slipping past traditional defenses such as blacklists and rule-based filters. Existing detection models, including SVM, XGBoost, and CNN, have improved accuracy but still depend heavily on manually crafted features and struggle to adapt to new or evolving attack patterns. This challenge creates the need for a more flexible and intelligent detection approach capable of learning and adapting to emerging email threats. This study aims to develop an ensemble phishing email detection model combining SVM and XGBoost, optimize it using Bayesian tuning, and evaluate its performance through accuracy, precision, recall, F1-score, and ROC-AUC metrics. This study used an ensemble approach that combines SVM and XGBoost to detect phishing emails. Various SVM models, including Baseline, Grid Search, SGD, and Bayesian-optimized versions, were developed and tested. An optimized Bayesian model was developed to improve accuracy, with performance evaluated using accuracy, precision, recall, F1-score, and ROC-AUC. A well-known Kaggle phishing dataset was used for fair comparison. After cleaning and reducing 10,000 emails with 1,250 features to 9,872 emails and 500 cleaned features, the Baseline SVM reached 0.9287 accuracy, Grid Search SVM improved to 0.96, and SGD SVM slightly dropped to 0.92. The Bayesian SVM performed best at 0.9667, showing greater stability and generalization. The Bayesian-optimized Hybrid Ensemble SVM–XGBoost achieved 0.992 accuracy and 0.9992 ROC-AUC, confirming its strong reliability and effectiveness in phishing detection. Stacking substantially enhanced model stability, generalization, and real-time reliability for phishing detection. Description: N/A Mon, 01 Dec 2025 00:00:00 GMT http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30908 2025-12-01T00:00:00Z