Enhanced Healthcare Data Security Through MI-Based Cyberattack Detection in SDN

It is critical to protect sensitive data against hackers in the healthcare industry. Although they are used for effective resource management and security, software-defined networks, or SDNs, are susceptible to many types of assaults. A machine learning-based cyberattack detector (MCAD) designed specifically for healthcare systems is presented in this research. Enhancing network security, the system uses an adapted layer three (L3) learning switch application to collect and analyze normal and anomalous traffic, and then deploys MCAD on the Ryu controller. Many machine learning algorithms, such as Random Forest, Gradient Boosting Machines, Support Vector Machines, K Nearest Neighbors, Isolation Forest, Deep Neural Networks, Convolutional Neural Networks and XGBoost, are used in the study to assess MCAD's performance. The outcomes show how MCAD may enhance network efficiency, boost throughput, and lower latency and jitter, thereby bolstering the security of healthcare applications. Index Terms—Cybersecurity, machine learning, healthcare security, SDN security, anomaly detection, network intrusion detection, deep learning,