Innovative Cyberattack Detection Mechanism for Hospital Management System Using Hybrid Deep Learning Algorithm

Abstract

The simulation focused on assessing the vulnerabilities and potential impacts of cyberattacks within the healthcare sector, specifically in a hospital environment. Various attack scenarios, including ransomware, distributed denial-of-service (DDoS) attacks, and unauthorized access to patient records, were simulated to gauge the extent of potential damage. The cybersecurity team successfully identified weak points and devised strategies to mitigate these risks. To enhance detection and response capabilities, a machine learning-based mechanism was implemented, leveraging algorithms like support vector machines, random forest, and deep learning models. This mechanism analyzes real-time network traffic data, identifying deviations from normal behavior such as unusual data transfer patterns, unauthorized access attempts, or abnormal system behaviors. Trained on labeled datasets, these algorithms classify network traffic into normal or potentially malicious activities. The system's continuous learning capabilities enable it to adapt and improve detection as new attack patterns emerge. Overall, the simulation, coupled with the advanced detection mechanism, empowers the cybersecurity team to proactively safeguard patient data, ensure uninterrupted healthcare services, and fortify critical infrastructure against evolving cyber threats, thereby enhancing their understanding of vulnerabilities and bolstering incident response capabilities. © 2024 IEEE.