MedAIScout: Automated Retrieval of Known Machine Learning Vulnerabilities in Medical Applications
Abstract
Machine learning (ML)-enabled medical devices are transforming the healthcare industry but are vulnerable to adversarial attacks that can compromise their safety. Current red teaming efforts often overlook these ML-specific threats, leaving devices exposed. To address this, we present MedAIScout, a semi-automated tool designed to retrieve information on known ML vulnerabilities relevant to ML-enabled medical devices. Through case studies on five FDA-approved ML-enabled devices, we demonstrate that MedAIScout effectively identifies relevant vulnerabilities, significantly aiding red teaming efforts
Cite
Text
Dharmalingam and Mitra. "MedAIScout: Automated Retrieval of Known Machine Learning Vulnerabilities in Medical Applications." NeurIPS 2024 Workshops: Red_Teaming_GenAI, 2024.Markdown
[Dharmalingam and Mitra. "MedAIScout: Automated Retrieval of Known Machine Learning Vulnerabilities in Medical Applications." NeurIPS 2024 Workshops: Red_Teaming_GenAI, 2024.](https://mlanthology.org/neuripsw/2024/dharmalingam2024neuripsw-medaiscout/)BibTeX
@inproceedings{dharmalingam2024neuripsw-medaiscout,
title = {{MedAIScout: Automated Retrieval of Known Machine Learning Vulnerabilities in Medical Applications}},
author = {Dharmalingam, Athish Pranav and Mitra, Gargi},
booktitle = {NeurIPS 2024 Workshops: Red_Teaming_GenAI},
year = {2024},
url = {https://mlanthology.org/neuripsw/2024/dharmalingam2024neuripsw-medaiscout/}
}