http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/53 Cyber Security Science 2026-05-02T14:36:27Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30066 Title: Layered and hierarchical approach for modelling multidimensional design threats Authors: Ojeniyi, Joseph Adebayo; Waziri, Victor Onomza; Aibinu, Abiodun Musa; Inyiama, H. C. Abstract: Security of any digitally designed system is not guaranteed until an appropriate modelling and assessemtn of threat is carried out and proper mitigation is iteratively done. 2016-01-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30065 Title: Improving Digital Forensics Analysis in Federated Domains through Estimator Analysis and Network Flow Optimization Authors: Ojeniyi, Joseph Adebayo; Longe, O. B.; Oguntade, E. S. Abstract: Digital Forensics is a field that deals with safe and unaltered collection of vital data from the scene of crime incidence for the purpose of investigation and prosecution. Different tools have been developed to help in analysing or estimating the degree or extent of the criminality. However, the exponential growth and expansion being experienced in field of computing and networking is making these estimations or forensic analysis more or less accurate. Some of the reasons militating against effective analysis are attributed to various inhibiting policies across different platforms, routers, domains of networking. In this paper, some tools used for forensics analysis or estimating the probative values of digital evidence are referred to estimators. Three of these estimators are selected and tested in a simulated environment. Analysis of three digital forensics estimators (EnCase, Safeback and TootKit) is carried out in this paper. This is experimentally aided by simulation of heterogeneous domain-based network and packet analyzer is used to collect probability reading in the packet option field at each hop along the communication path between an attacker and the victim. The graphical analysis with varied initial values shows that estimation accuracies of the estimators reduce irrespective of initial values. With the developed model, the router could be configured for packet boosting at the point of dwindling probabilities using Maximum Network Flow Algorithm 2016-01-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30064 Title: Enhanced Security Testbed Threat Model Based on Parametric Equation and Multi-Level Design Approach Authors: Ojeniyi, Joseph Adebayo; Waziri, Victor Onomza; Aibinu, Abiodun Musa; Inyiama, H. C. Abstract: The threat model of a security testbed provides quantitative and qualitative conceptual insights into robustness of the developed testbed. Security of any digitally designed system is not guaranteed until an appropriate modelling and assessment of threat is carried out and proper mitigation is iteratively done. Several existing techniques could not handle the complexities, multi-dimensionality and layered nature inherent in threat modelling of multi-layered systems. Most approaches focus on a single level of data communication. This article aims to develop a threat model that considers different levels and dimensions of data communications over a network architecture. Parametric-based equation and data flow diagrams were used in the modelling. The model was iteratively assessed and evaluated to ensure conformity with pre-defined security requirement for the testbed. 2016-01-01T00:00:00Z http://irepo.futminna.edu.ng:8080/jspui/handle/123456789/30063 Title: Development of a hybridized CNN-BiGRU Framework for detection of website phishing attacks Authors: Egigogo, A. R.; Ismaila, Idris; Olalere, Morufu; Abisoye, O. A.; Ojeniyi, Joseph Adebayo Abstract: Phishing remains a major cybersecurity challenge, with attackers using deceptive tactics to trick users into disclosing confidential data. Traditional detection systems, which often rely on fixed features or predefined rules, struggle to keep up with rapidly evolving phishing strategies. This research introduces a deep learning-based solution that combines Convolutional Neural Networks (CNN) and Bidirectional Gated Recurrent Units (BiGRU) to improve phishing website detection. The CNN component is responsible for learning spatial patterns from web data, while the BiGRU layer captures sequential relationships, providing a more complete understanding of the underlying threats. The framework involves meticulous preprocessing steps such as data cleaning, normalization through MinMax scaling, and optimal feature selection using the SelectKBest, CNN and BiGRU methods. The model was trained and tested on large scale, publicly available datasets from IEEE Data Port and Mendeley, consisting of over 250,000 URL entries. Through train-test split and cross-validation techniques, the model consistently achieved outstanding results: 99.96% accuracy, 99.92% precision, 100% recall, and a 99.92% F1 score. When compared to existing solutions, this hybrid approach sets a new performance benchmark, underscoring the power of combining spatial and temporal deep learning methods in defending against phishing threats. 2025-01-01T00:00:00Z