Systems-Theoretic and Data-Driven Security Analysis in ML-enabled Medical Devices
Not on the map. Why?
Abstract (arXiv)
The integration of AI/ML into medical devices is rapidly transforming healthcare by enhancing diagnostic and treatment facilities. However, this advancement also introduces serious cybersecurity risks due to the use of complex and often opaque models, extensive interconnectivity, interoperability with third-party peripheral devices, Internet connectivity, and vulnerabilities in the underlying technologies. These factors contribute to a broad attack surface and make threat prevention, detection, and mitigation challenging. Given the highly safety-critical nature of these devices, a cyberattack on these devices can cause the ML models to mispredict, thereby posing significant safety risks to patients. Therefore, ensuring the security of these devices from the time of design is essential. This paper underscores the urgency of addressing the cybersecurity challenges in ML-enabled medical devices at the pre-market phase. We begin by analyzing publicly available data on device recalls and adverse events, and known vulnerabilities, to understand the threat landscape of AI/ML-enabled medical devices and their repercussions on patient safety. Building on this analysis, we introduce a suite of tools and techniques designed by us to assist security analysts in conducting comprehensive premarket risk assessments. Our work aims to empower manufacturers to embed cybersecurity as a core design principle in AI/ML-enabled medical devices, thereby making them safe for patients.
Key facts. No citing papers in the map yet (data through 14 Oct 2026). Builds on 23 of its 117 references that are in the map. First posted on arXiv 18 Jun 2025.
Builds on
23 of 117 references.
References · 23
- 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language Modelscited by 12,459
- 2023CAMEL: Communicative Agents for "Mind" Exploration of Large Language Model Societycited by 1,395
- 2023Role-Play with Large Language Modelscited by 294
- 2017Tactics of Adversarial Attack on Deep Reinforcement Learning Agentscited by 166
- 2019Understanding Adversarial Attacks on Deep Learning Based Medical Image Analysis Systemscited by 153
- 2018Adversarial Attacks Against Medical Deep Learning Systemscited by 62
- 2023TELeR: A General Taxonomy of LLM Prompts for Benchmarking Complex Taskscited by 49
- 2020Adversarial Attack Vulnerability of Medical Image Analysis Systems: Unexplored Factorscited by 40
- 2018Identify Susceptible Locations in Medical Records via Adversarial Attacks on Deep Predictive Modelscited by 15
- 2024Engineering Safety Requirements for Autonomous Driving with Large Language Modelscited by 14
- 2023Safety Analysis in the Era of Large Language Models: A Case Study of STPA using ChatGPTcited by 13
- 2019Suspicion-Free Adversarial Attacks on Clustering Algorithmscited by 11
11 more
- 2019ECGadv: Generating Adversarial Electrocardiogram to Misguide Arrhythmia Classification Systemcited by 10
- 2019Understanding the One-Pixel Attack: Propagation Maps and Locality Analysiscited by 10
- 2021Jekyll: Attacking Medical Image Diagnostics using Deep Generative Modelscited by 10
- 2015Adverse Events in Robotic Surgery: A Retrospective Study of 14 Years of FDA Datacited by 9
- 2023DKEC: Domain Knowledge Enhanced Multi-Label Classification for Diagnosis Predictioncited by 8
- 2024Welcome Your New AI Teammate: On Safety Analysis by Leashing Large Language Modelscited by 8
- 2023STPA for Learning-Enabled Systems: A Survey and A New Practicecited by 7
- 2021Explanation-Guided Diagnosis of Machine Learning Evasion Attackscited by 6
- 2022Design and Validation of an Open-Source Closed-Loop Testbed for Artificial Pancreas Systemscited by 6
- 2022Adversarial Artifact Detection in EEG-Based Brain-Computer Interfacescited by 4
- 2015Systems-theoretic Safety Assessment of Robotic Telesurgical Systemscited by 2
Built on by
Not cited yet.