# A Novel Framework for Threat Analysis of Machine Learning-based Smart Healthcare Systems

arXiv: https://arxiv.org/abs/2103.03472 · HTML: https://mlsanity.com/paper/2103.03472/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 5 of its 58 references that are in the map.
- First posted on arXiv 5 Mar 2021.

## Builds on (most cited first, 5 of 5)

- [Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks](https://mlsanity.com/paper/1702.01135/) (2017)
- [Output Range Analysis for Deep Neural Networks](https://mlsanity.com/paper/1709.09130/) (2017)
- [Verification for Machine Learning, Autonomy, and Neural Networks Survey](https://mlsanity.com/paper/1810.01989/) (2018)
- [Adversarial Attacks to Machine Learning-Based Smart Healthcare Systems](https://mlsanity.com/paper/2010.03671/) (2020)
- [HealthGuard: A Machine Learning-Based Security Framework for Smart Healthcare Systems](https://mlsanity.com/paper/1909.10565/) (2019)

## Built on by (most cited first, 1 of 1)

- [XAI for Cybersecurity: State of the Art, Challenges, Open Issues and Future Directions](https://mlsanity.com/paper/2206.03585/) (2022)

## Abstract (arXiv)

Smart healthcare systems (SHSs) are providing fast and efficient disease treatment leveraging wireless body sensor networks (WBSNs) and implantable medical devices (IMDs)-based internet of medical things (IoMT). In addition, IoMT-based SHSs are enabling automated medication, allowing communication among myriad healthcare sensor devices. However, adversaries can launch various attacks on the communication network and the hardware/firmware to introduce false data or cause data unavailability to the automatic medication system endangering the patient's life. In this paper, we propose SHChecker, a novel threat analysis framework that integrates machine learning and formal analysis capabilities to identify potential attacks and corresponding effects on an IoMT-based SHS. Our framework can provide us with all potential attack vectors, each representing a set of sensor measurements to be altered, for an SHS given a specific set of attack attributes, allowing us to realize the system's resiliency, thus the insight to enhance the robustness of the model. We implement SHChecker on a synthetic and a real dataset, which affirms that our framework can reveal potential attack vectors in an IoMT system. This is a novel effort to formally analyze supervised and unsupervised machine learning models for black-box SHS threat analysis.