Claim Missing Document
Check
Articles

Found 2 Documents
Search

A Proactive Framework for Detecting and Preventing Zero-Day Attacks in Modern Network Environments Shareefullah Mosazai; Ikramullah Maroof; Islahuddin Jalal
INTERNATIONAL JOURNAL ON ADVANCED TECHNOLOGY, ENGINEERING, AND INFORMATION SYSTEM Vol. 5 No. 3 (2026): AUGUST
Publisher : Transpublika Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55047/ijateis.v5i3.2403

Abstract

Zero-day attacks exploit software and network vulnerabilities that are unknown to vendors and defenders, leaving signature-based intrusion detection systems structurally unable to respond before damage occurs. This study proposes a proactive framework that combines unsupervised anomaly detection, ensemble supervised learning, and automated response orchestration to detect and contain previously unseen attacks in modern network environments. The framework integrates a deep autoencoder for reconstruction-based anomaly scoring, an isolation forest for density-based outlier isolation, and a gradient-boosted ensemble for supervised refinement, whose outputs are fused through a weighted threat-scoring module aligned with the MITRE ATT&CK matrix. Detected anomalies trigger an orchestration layer that automatically quarantines affected hosts, updates software-defined network rules, and redirects suspicious traffic to deception environments for analysis. The framework was evaluated on benchmark network-traffic corpora (UNSW-NB15 and CIC-IDS2017) using zero-day scenarios constructed by withholding entire attack categories from training. Results indicate that the hybrid framework achieves higher detection accuracy and a substantially lower false-positive rate than individual base learners and a conventional signature-based baseline, while maintaining detection latency compatible with near-real-time response. These findings suggest that combining complementary unsupervised and supervised models within a proactive orchestration pipeline meaningfully improves resilience against zero-day threats compared with reactive, signature-dependent defenses. The paper further discusses architectural trade-offs, deployment considerations, and directions for future work on adversarial robustness and cross-domain generalization.
Artificial Intelligence-Based Human Behavior Analysis for Reducing Cybersecurity Risks and Human Errors Ikramullah Maroof; Shareefullah Mosazai; Islahuddin Jalal
INTERNATIONAL JOURNAL ON ADVANCED TECHNOLOGY, ENGINEERING, AND INFORMATION SYSTEM Vol. 5 No. 3 (2026): AUGUST
Publisher : Transpublika Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55047/ijateis.v5i3.2404

Abstract

Human behavior remains one of the most persistent contributors to cybersecurity incidents, as unintentional errors, social-engineering susceptibility, and insider misuse continue to bypass purely technical safeguards. This conceptual, literature-based study examines how artificial intelligence (AI) and machine learning (ML) techniques can be applied to analyze human behavioral patterns in order to reduce cybersecurity risk and human error within organizational information systems. Drawing on a structured review of insider-threat detection, phishing and social-engineering research, security-awareness training studies, and explainable-AI literature, the study synthesizes recurring behavioral indicators, modeling approaches, and evaluation practices reported across the field. A conceptual AI-based human-behavior-analysis framework is proposed, comprising data acquisition, behavioral feature engineering, AI/ML modeling, explainable risk scoring, and adaptive human-in-the-loop response. The review indicates that sequence-aware deep-learning models, such as long short-term memory networks and autoencoders, combined with explainable AI techniques, achieve strong reported detection performance while preserving analyst interpretability, and that adaptive, behavior-based training interventions are associated with measurably greater reductions in human-related risk than static, one-time awareness programs. The study concludes that integrating continuous behavioral analytics with human-centered training and feedback mechanisms offers a more resilient approach to cybersecurity risk management than technology-only or training-only strategies. Implications for organizational security governance, model interpretability, and future empirical validation are discussed.