Bridging the Cybersecurity Divide: A Systematic Review of AI And Lightweight Monitoring for Resource-Constrained Institutions

The digital transformation has exacerbated a critical cybersecurity divide, systematically excluding low-resource institutions for example schools, NGOs, and SMEs from modern network protection due to profound constraints in budget, hardware, and expertise. While research in network monitoring has advanced, featuring sophisticated AI for anomaly detection and cloud-based orchestration, its applicability to constrained environments remains critically underexplored. This study conducts a systematic literature review of 150 peer-reviewed works (2018-2025) to map the state-of-the-art and evaluate its alignment with the needs of low-resource settings. Our analysis, structured across four thematic areas namely AI Anomaly Detection, Lightweight Monitoring, Cloud Integration, and Configuration Management reveals a pervasive convergence gap. We identify that research excels in technological silos but fails at their intersection: AI models are computationally prohibitive, lightweight solutions lack adaptive intelligence, cloud frameworks assume stable connectivity, and configuration tools operate in isolation. This siloed progression creates a landscape where solutions are either too bulky, too simple, too cloud-dependent, or too complex for practical deployment in target institutions. The primary contribution of this review is the articulation of four core requirements for a new holistic paradigm: (1) Resource-Aware AI, (2) Progressive Intelligence, (3) Intermittent-Cloud Resilience, and (4) a Unified Management Plane. In direct response, we propose the development of a lightweight, AI-cloud-integrated platform as a direct path forward. This review synthesizes a fragmented field and provides a definitive research agenda aimed at bridging the cybersecurity divide through architectural convergence.