https://matjournals.net/engineering/index.php/JCSPIC <p><strong>JCSPIC</strong> is a peer reviewed journal of Computer Science domain published by MAT Journals Pvt. Ltd. It is a print and e-journal focused towards the rapid publication of research and review papers based on all areas of security and privacy including Security in Business, Healthcare and Society, Information Security, Communication Security, and Privacy. Topics related to Biometric--based Security, Cryptography Systems, Critical Infrastructure Security, Application Security, Network Security, Data Loss Prevention, Information Security, Cloud Security, End-User Education, Software Development Security, Security Operations, Physical Security, Embedded Security, Data Analytics for Security and Privacy, Integrated Security Design Schemes, Surveillance, Firewalls, Router and Switch Security, Email Filtering, Vulnerability Scanning, Intrusion Detection and Prevention System (IDS/IPS), Host-based Security Tools, Critical Infrastructures and Key Resources. Research Papers related to Cyber Threat Intelligence and Analytic Solutions, such as Big Data, Artificial Intelligence, and Machine Learning, to Perceive, Reason, Learn, and Act against Cyber Adversary Tactics, Techniques, and Procedures will also be considered.</p> en-US Journal of Cyber Security, Privacy Issues and Challenges https://matjournals.net/engineering/index.php/JCSPIC/article/view/3620 <p><em>Cyberattacks are becoming more sophisticated and frequent, creating major challenges for modern digital infrastructures. Conventional cybersecurity systems mainly depend on reactive defense strategies and static detection techniques, which are often inadequate for identifying emerging and complex threats. To overcome these limitations, this research introduces an optimized temporal fusion transformer (OTFT) framework for the classification and prediction of significant cyber incidents (SCI). The proposed approach combines temporal feature extraction, gated residual learning, recurrent processing, and multi-head attention mechanisms to analyze complex cybersecurity event sequences effectively. Unlike traditional sequential models, the proposed framework can learn both immediate behavioral changes and long-term temporal relationships from multivariate cyber datasets. An adaptive dynamic population control-based polar bear optimization algorithm (DPCPBOA) is further integrated to optimize critical hyperparameters, improve convergence speed, and minimize overfitting during training. The framework was evaluated using benchmark cybersecurity datasets containing large-scale attack records and temporal event information. Experimental analysis demonstrates that the OTFT model achieves superior predictive performance compared with conventional machine learning and deep learning approaches, including LSTM and Seq2Seq architectures. The proposed framework achieved high accuracy, precision, recall, and F1-score while maintaining strong robustness and generalization capability. The overall findings indicate that the proposed model can serve as an intelligent and scalable solution for proactive cyber threat forecasting and advanced cybersecurity management. </em></p> Ajitha I. A. Devi Copyright (c) 2026 Journal of Cyber Security, Privacy Issues and Challenges 2026-05-26 2026-05-26 1 12