Machine Learning Based Detection For Cyber Attacks In Internet Of Medical Things Devices

My machine learning skills continue to grow! During summer 2024, I researched machine learning based detection for cyber attacks in IoMT devices. I noticed a problem in the healthcare industry, the vulnerability of IoMT devices to cyber attacks and the devastating consequences of such attacks, and I sought to use technology to solve it. I developed the project in Jupyter Notebook using Python and libraries such as Matplotlib, Numpy, Pandas, and Scikit Learn. I learned a lot about how different machine learning models work and which cases they are best suited for, from Isolation Forests to Neural Networks, and my greatest success was training a Decision Tree model to detect ARP Spoofing attacks on Wifi and MQTT IoMT devices, which was 97% accurate in its detection. I presented my research at the IEEE MIT Undergraduate Research Technology Conference (URTC) in October, and my research paper is published in the IEEE Digital Xplore Library (check it out here!). I am also a finalist for the National Center for Women & Information Technology (NCWIT) Aspirations in Computing Collegiate Award!