Cyber threat estimation and prevention using xgboost

Abstract

The health care industry is vulnerable to cyber threats, and effective identification and classification of these threats can help healthcare organizations proactively take measures to prevent and mitigate them. This paper presents a classification model using the XGBoost algorithm to classify different types of cyber threats in the healthcare industry like malware, DDoS, reconnaissance, generic and exploits. The model uses a variety of features, including network traffic and log data, to predict the type and severity of cyber threats. The paper evaluates the model's performance using a dataset of real-world cyber threats and demonstrates its effectiveness in accurately classifying cyber threats. The paper also discusses the potential benefits of using this model to help healthcare organizations better protect patient data and mitigate the impact of cyber-attacks. Overall, the XGBoost-based classification model shows promise as a useful tool for identifying and managing cyber threats in the health care industry with accuracy of 99.40%.