Deep Learning-Driven Cybersecurity Threat Detection and Mitigation in Saudi Arabia Healthcare System

Cybersecurity threats in the healthcare industry, particularly in Saudi Arabia, pose significant challenges. As institutions adopt digital technologies under Saudi Arabia's Vision 2030, vulnerabilities to ransomware, phishing, and data breaches escalate. This paper investigates the role of Bidirectional Long Short-Term Memory (Bi-LSTM) and Convolutional Neural Networks (CNN) models in enhancing threat detection and mitigation strategies tailored to Saudi Arabia's unique healthcare requirements. The proposed model achieves 94 % accuracy, with high precision, recall, and F1-score, confirming its reliability in identifying cyber threats. Additionally, we introduce a hybrid deep learning architecture that integrates real-time threat monitoring and adaptive mitigation strategies. Experimental results demonstrate its effectiveness in safeguarding sensitive health care data and ensuring service continuity. These findings underscore the potential of deep learning in strengthening cybersecurity defenses in critical sectors.