Explainable ML-based DoS Attack Detection Framework for Reliable Telesurgery Systems

The emergence of smart healthcare has transformed the delivery of medical services. It increased the reliability issues related to telesurgery system. Robotic technologies integrate to achieve surgical precision in countless medical fields. But, this increased connectivity has raised concerns about vulnerability to denial of service (DoS) attacks that can disrupt operations and affect users' safety. In this paper, we propose an explainable machine learning (ML) framework for detecting DoS attacks in telesurgery environments. Our framework utilizes several ML algorithms, including K-Nearest Neighbors (KNN), Decision Tree (DT), XGBoost (XGB), and Logistic Regression (LR), to analyze network traffic and distinguish between legitimate and malicious signals. Here, XGB achieves the highest accuracy at 0.8967, making it a good choicefor this application. We also used the concepts of Explainable AI (XAI) such as SHAP and LIME to enhance decision-making process of our models. We aim to build trust among healthcare providers and ensures the safe conduct of robotic telesurgery operations and smart healthcare solutions by improving the interpretation of research and providing information on performance metrics such as accuracy, precision, recall, F1 scores, and ROC curves.