FortiSMB: AI-Driven Insider Threat Detection and Explainable Security System for Mental-Health SMBs

FortiSMB: AI-Driven Insider Threat Detection and Explainable Security System for Mental-Health SMBs presents an intelligent cybersecurity framework designed to detect insider threats in mental-health small and medium-sized businesses (SMBs). The system combines behavioral anomaly detection using machine learning with explainable artificial intelligence (XAI) techniques to improve transparency and trust in security decisions. FortiSMB employs a dual-stage risk stratification process, anomaly detection, RBAC-based policy validation, and explainability methods such as SHAP and LIME to provide actionable security insights. The framework is evaluated using the CERT Insider Threat Dataset as a proxy due to privacy limitations in healthcare environments. Results demonstrate the effectiveness of the system in identifying suspicious insider behavior while maintaining interpretability and supporting resource-constrained SMB environments.