http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/53 Cyber Security Science 2026-07-31T21:47:16Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31937 Title: Development of a Hybrid Anomaly-Based Intrusion Detection System Using Autoencoder and Isolation Forest Authors: Chinedu, Somtochukwu; Uduimoh, Andrew A; Anyaora, Peter; Alhassan, John k; Yusuf, Hadiza Abstract: As cyberattacks advance in sophistication and fluidity, modern intrusion detection systems (IDS) must progress from static, signature-based models to adaptive models that can detect known and zero-day threats (Labonne, 2020; Ali et al., 2023). This study proposes a hybrid anomaly-based IDS that integrates an Autoencoder (AE) for deep feature representation with an Isolation Forest (IF) for statistical anomaly scoring. The objective is to enhance detection performance for both known and zero-day attacks within an unsupervised learning framework. The proposed model is an adaptation of the hybrid AE–IF framework devised by Mohammed and Telek (2023) and the fog-computing adaptation by Sadaf and Sultana (2020). The hybrid model deploys a logical fusion framework—Hybrid OR and Hybrid AND—dynamically balancing precision and recall in anomaly detection. The model is implemented in Python and trained using unsupervised learning on two benchmark datasets, NSL-KDD and CICIDS2017, so the model operates without any prior knowledge of attack signatures (Engelen et al., 2021). Experimental responses to model anomaly detection capabilities support that the Hybrid OR configuration of the model provided the most balanced anomaly detection performance scores recording F1-score of 0.85 and 0.69 on NSL-KDD and CICIDS2017 datasets respectively—both hybrid performance metrics outperforming the stand-alone AE and IF models. These results are in line with more recent evidence supporting the position that combining feature-reconstruction learning with statistical isolation increases the resilience and adaptability towards network intrusion detection (Elsaid & Binbusayyis, 2024; Alhassan et al., 2024). While performance declined on the more complex CICIDS2017 dataset, the hybrid approach demonstrated improved generalisation relative to individual models. The results suggest that logical fusion of representation learning and isolation-based scoring provides a lightweight and adaptable framework for network intrusion detection, although further validation in live network environments is required before operational deployment (Abuabed et al., 2023; Wang et al., 2023). 2025-01-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31935 Title: Blockchain Based Zero Knowledge Proof Model for Secure Data Sharing Scheme in a Distributed Vehicular Networks Authors: Mohammad, Umar Majigi; Ismaila, Idris; Shafii, Abdulhamid M.; Richard, Adeyemi Ikuesan; Uduimoh, Andrew Anogie Abstract: The possibility of implementing advanced applications, such as improved driving safety, has increased with the rapid development of vehicular telematics, and existing vehicular services have been enriched through data sharing and analysis between vehicles. This research uses smart contracts and consortium blockchain zero knowledge proof to secure data sharing and storage in vehicular networks. The results indicate that, for message sizes (m), both data_ experiments _2 and 1 produce ciphertext of the same size, with the exception of 'gnfuv-temp-exp1-55d487b85b-5g2xh,' which generates ciphertext of 156 bits with the lowest decryption time of 26,865ms and a small decrease in encryption time between 28,620ms and 28,162ms. the proposed model validation shows that the model performed better than Advanced encryption standard in term of ciphertext size, encryption time and decryption time in comparison and it satisfies the good and robust blockchain-based zero knowledge proof model for secure data sharing and storage for distributed VANET. The scheme achieves high levels of security while operating with reasonable efficiency, reliability and availability according to numerical results. 2023-01-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31934 Title: SYSTEMATIC LITERATURE REVIEW ON MALICIOUS COMMAND AND CONTROL: TYPES, TECHNIQUES, TOOLS, CHALLENGES AND RESEARCH DIRECTIONS Authors: OJENIYI, JOSEPH A.; CEPHAS, ANYIGOR CHIGBO; SUBAIRU, S.O.; DOGONYARO, NOEL M.; SULEIMAN, AHMAD; ANDREW, UDUIMOH Abstract: Malicious Command and Control (C2) traffic is a critical enabler of modern cyberattacks, allowing remote management of compromised systems. This paper presents a systematic literature review (SLR) of 14 primary studies published between 2014 and 2025, identified via a structured PRISMA process across six databases (IEEE, ACM, EEE Xplore, etc.). The review synthesizes six dominant C2 models—centralized, P2P, DGA, fast-flux, cloud abuse, and encrypted traffic—and evaluates detection methods including DNS entropy and machine learning. Results indicate that while detection accuracy for P2P and DGA has improved, encrypted traffic and cloud-based C2 remain significant blind spots. We identify a critical need for explainable AI (XAI) and metadata-based analysis. This review provides a roadmap for researchers and practitioners to develop more resilient, automated threat detection frameworks. 2026-03-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/31933 Title: Detection of Cyberbullying on Facebook Twitter (X) Using Bi Directional Long Short‑Term Memory and ExtremeGradient Boost Algorithms Authors: Ojeniyi, Joseph Adebayo; Mohammed, Yusuf Adamu; Isah, Abdulkadir Onivehu; Anyaora, Peter Chizaramuekpere; Olusanjo, Fasola; Uduimoh, Andrew; Baba, Meshach Abstract: The social networking sites have transformed digital communication but have simultaneously enabled the escalation of harmful online behaviors, particularly cyberbullying. This recurring formofdigital aggression can lead to serious emotional and psychological harm, including anxiety, depression, and in severe cases, self‑inflicted injury or suicidal behavior. The timely identification and prevention of cyberbullying have become an essential focus of current research. Although numerous machine learning techniques have been applied to detect abusive content, many continue to face challenges such as inefficient kernel tuning, extended training durations, and re duced predictive accuracy. To address these limitations, this study presents a hybrid deep learning architecture that integrates a Bidirectional Long Short‑Term Memory (BiLSTM) network with the Extreme Gradient Boosting (XGBoost) algorithm to improve contextual awareness and classification accuracy. The proposed framework was trained and evaluated on datasets collected from Facebook and X (formerly Twitter), capturing diverse linguistic and behavioral characteristics of user interactions. Experimental results indicate that the BiLSTM–XGBoost hybrid model outperforms conventional classifiers by effectively managing context representation, adaptive learning, and class imbalance. The model achieved 97% accuracy, 95% precision, 92% recall, and an F1‑score of 96%, confirm ing its robustness and efficiency for cyberbullying detection in dynamic social media environments. The study helps educational institutions, online platforms and legal frameworks provide insights into how to better identify cyberbullying in real‑world scenarios. The study’s high recall ensures that cyberbullies are easily identified and it enhances the understanding of how combining multiple models can lead to better performance in cyberbullying detection. 2026-07-01T00:00:00Z