Identifying Protected Health Information in Hacker Communities: A Multi-Task Relation Learning Approach
In Plain Terms
Stolen medical records are increasingly bought and sold in encrypted chat groups on platforms like Telegram and Discord, buried in huge amounts of unrelated chatter. This paper introduces PHI-NEXT, a system that automatically finds those posts, pulls out what kind of health information is being traded, and tracks how the activity changes over time. It outperforms existing detection methods and gives security teams and regulators a practical way to monitor this underground market at scale.
Watch a short video summary
Artifacts
No artifacts listed yet.
Related Papers
Cite this
APA Dacosta, C., Ampel, B. M., Hashim, M., & Chen, H. (2026). Identifying Protected Health Information in Hacker Communities: A Multi-Task Relation Learning Approach. Journal of Management Information Systems.
BibTeX
@article{dacosta2026identifying,
title={Identifying Protected Health Information in Hacker Communities: A Multi-Task Relation Learning Approach},
author={Cade Dacosta and Benjamin M. Ampel and Matthew Hashim and Hsinchun Chen},
journal={Journal of Management Information Systems},
year={2026}
}
Benjamin M. Ampel
Assistant Professor in Computer Information Systems and Director, Center for CyberAI Research (CCAIR)
My research focuses on AI-enabled Cybersecurity, including Cyber Threat Intelligence, Large Language Models, and Phishing Detection.