The Roadmap to Classify Malware Using ML Algo Through IOT Based SN

Therefore, the Internet of Things has revolutionized the daily life of human beings with smart devices and systems, and many healthcare systems have advanced greatly in recent years. However, recent cyberattacks have shown the security flaw of current IoT in healthcare environments. Generally, current security solutions based on the classic paradigms of network security cannot adequately face the challenges posed by the particular behaviors of the IoT environments, since most of the protocols that are present show atypical behaviors, and resources are limited. In this sense, it is clear and urgent to create specific tools, methodologies, and datasets for the IoT. In light of the foregoing, we propose a new paradigm to develop context-aware security solutions also suitable for the IoT settings. The solution should be aimed at achieving the goal: Malicious communications detection. Development of open source program IoT-Flock, which can simulate IoT devices benign and malicious, as a base to test and improve IoT security; Development of a utility to convert the collected traffic into standard IoT dataset to be used for further analysis and research; and As a proof of concept, we create an IoT healthcare dataset from benign and attack scenarios. We use several machine learning techniques to analyze the data and detect cyber-attacks, thus fortifying security from threats that might occur in a healthcare system..