Abstract:
As the healthcare sector increasingly adopts digital technologies, the need for robust cybersecurity measures has become paramount. This project introduces an Anomaly-Based Intrusion Detection System (IDS) designed to strengthen the security of Electronic Health Records (EHR) by detecting unauthorized access. Unlike traditional signature-based IDS, which relies on predefined attack patterns, our system analyzes user behavior in context, taking into account factors like access time and device used to identify abnormal activities. This project is developed using Python and Flask and uses machine learning algorithms to adapt and improve system continuously. The System effectively identifies unknown threats while minimizing false positives, thus enhancing the protection of sensitive patient data. Additionally, it has a user-friendly dashboard for healthcare administrators to monitor access logs, generate reports, and visualize anomalies in a clear, graphical format. This research highlights the growing need for advanced security solutions in healthcare and addresses the shortcomings of existing systems. This project offers an effective way to detect and mitigate cyber threats, our Anomaly-Based IDS contributes to securing patient information and making a safer healthcare environment. The findings add to the ongoing conversation about cybersecurity in healthcare, stressing the importance of proactive defense measures in the face of rising cyber risks.
