Detecting AI-Generated Phishing Attacks Targeting IoMT Devices in Healthcare Using Machine Learning
Publication Date
2025
Presentation Length
15 minutes
College
College of Sciences & Mathematics
Department
Math and Computer Science, Department of
Student Level
Undergraduate
SPARK Category
Scholarship
Faculty Advisor
Dr. Tisha Gaines
SPARK Session
MTH/CSC Senior Presentations, Dr. Mary Goodloe, 3:15 - 4:15, College of Sciences & Mathematics
Presentation Type
Talk/Oral
Summary
With the increasing integration of IoMT devices in healthcare, AI-generated phishing attacks pose significant cybersecurity threats. This study explores the use of machine learning techniques, including Random Forest, K-Means Clustering, CNN, and LSTM to detect phishing attempts based on network traffic features.By leveraging these anomaly detection methods, we can effectively identify patterns in network traffic that indicate potential phishing attacks. Clustering techniques are used to categorize anomalies into distinct phishing attack behaviors, while deep learning models analyze sequential network data to enhance detection accuracy. Our approach compares traditional anomaly detection methods against advanced deep learning techniques, analyzing feature importance to determine the most relevant network indicators of phishing activity. The research seeks to develop an AI-driven Intrusion Detection System (IDS) capable of recognizing phishing attempts in real time and triggering alerts, thereby enhancing cybersecurity in IoT-driven healthcare environments.
Recommended Citation
McLeod, A., & Dolezel, D. (2018). Cyber-analytics: Modeling factors associated with healthcare data breaches. International Journal of Medical Informatics, 114, 133–140. https://doi.org/10.1016/j.ijmedinf.2018.02.006 Hussain, F., Abbas, S. G., Shah, G. A., Pires, I. M., Fayyaz, U. U., Shahzad, F., Garcia, N. M., & Zdravevski, E. (2021). A Framework for Malicious Traffic Detection in IoT Healthcare Environment. Sensors, 21(9), 3025. https://doi.org/10.3390/s21093025
