ENHANCING THE CYBER RESILIENCE OF INFORMATION SYSTEMS THROUGH  MACHINE LEARNING.

Ndung’u H., Munyao V., Karani J.,Wasike J.

Ndung’u H., Munyao V., Karani J.,Wasike J. Kirinyaga University, Kenya , Karatina University, Kenya

Keywords: Machine Learning; Cyber Resilience; Cybersecurity; Intrusion Detection; Threat Detection; Incident Response; Anomaly Detection; Adaptive Cyber Defense; Information Systems; Adversarial Machine Learning.

Abstract

Organizations today operate in an environment of relentless cyber threats that jeopardize continuity of critical services. Conventional security approaches, primarily focused on preventing intrusions, have
proven insufficient. This shortfall has shifted attention to cyber resilience, defined as organizations' capacity to maintain operations and recover effectively after cyber disruptions. Among the technologies
driving resilience, Machine Learning (ML) stands out for its ability to analyze vast datasets, identify anomalies, and respond effectively to evolving threats. Its ability to process vast and complex datasets
enables detection of subtle, hidden patterns that conventional tools or human analysts might overlook.To examine ML’s role in strengthening cyber resilience, this study undertook a systematic review of
recent literature (2020–2026). The review encompasses 87 peer‑reviewed studies from reputable sources, with the aim of mapping ML applications across different stages of resilience and identifying recurring
benefits and challenges. The goal is to provide a clear understanding of how ML contributes to resilience, evaluate its performance in practice, and identify the key challenges that must be overcome to ensure its
safe and robust adoption. Results show that ML significantly enhances resilience by enabling proactive threat detection and adaptive response mechanisms. However, challenges such as data quality, model
robustness, and the need for human oversight limit its effectiveness. The evidence suggests that ML is not a standalone solution but rather an enabling technology whose success depends on thoughtful
design, integration with human expertise, and mitigation of inherent limitations. This paper contributes a structured framework for understanding ML’s role in cyber resilience and highlights critical issues
that warrant further investigation, offering a foundation for both practitioners and researchers to advance resilient cybersecurity strategies.