I-Corps: Smart Healthcare System Threat Analyzer

该I-Corps项目的更广泛影响/商业潜力侧重于评估智能医疗系统（SHS）的安全性，旨在说服医疗设备制造商和医疗机构部署更安全的架构。医疗物联网（IoMT）技术的出现为SHS带来了许多增强和可能性，提供了收集健康信息和实现实时通信的机会，提高了医疗传感器的效率，并减少了疾病检测和治疗之间的延迟。COVID-19大流行增加了患病率，并增加了对远程和自动化患者监测的需求。然而，随着网络攻击的兴起，安全和可靠的SHS操作的重要性和优先级大大增加。这种安全部署旨在直接或间接地为从医疗保健提供者到患者的各种利益相关者提供服务。该项目将探索实施和商业化的机会，初步应用重点是为基于物联网的SHS开发安全和弹性分析。该I-Corps项目开发了一个系统，以减少基于无线传感器设备和植入式医疗设备的智能医疗系统（SHS）的潜在漏洞。 拟议的正式威胁分析工具旨在适用于任何使用机器学习模型从连续数据馈送中做出实时控制决策的医疗保健系统。该工具从有监督和无监督的机器学习模型中获取控制逻辑，以执行潜在威胁的正式合成。该解决方案使用最先进的方法，使用系统设置和对抗知识、可访问性、能力和攻击目标作为输入来识别可能的威胁。初步结果表明，所提出的技术可以提高SHS的鲁棒性和弹性。该工具识别的威胁向量可用于重新配置SHS架构，使其不易受到威胁。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project focuses on assessing the security of smart healthcare systems (SHSs), aiming to persuade both the manufacturers of medical devices and healthcare organizations to deploy a more secure architecture. The advent of internet-of-medical-things (IoMT) technology brings many enhancements and possibilities for SHSs by providing opportunities to collect health information and enable real-time communication, increasing the efficiency of medical sensors, and reducing the latency between disease detection and treatment. The COVID-19 pandemic has increased the prevalence and need for remote and automated patient monitoring. However, with the rise of cyberattacks, secure and dependable operation of SHSs has greatly increased in importance and priority. This secure deployment seeks to directly or indirectly serve various stakeholders ranging from healthcare providers to patients. The project will explore implementation and commercialization opportunities with an initial application focus on developing security and resilient analytics for IoMT-based SHSs.This I-Corps project develops a system to reduce the potential vulnerability of smart healthcare systems (SHSs) based on wireless sensor devices and implantable medical devices. The proposed formal threat analysis tool is designed to be applicable to any healthcare systems that use machine learning models to make real-time control decisions from continuous data feeds. The tool acquires control logic from machine learning models, supervised and unsupervised, to perform a formal synthesis of potential threats. Using a state-of-the-art method, the solution identifies possible threats using system settings and adversarial knowledge, accessibility, capability, and attack targets as inputs. Initial results suggest that the proposed technology can improve the robustness and resiliency of SHSs. The threat vectors identified by the tool can be utilized to reconfigure the SHS architecture to make it less susceptible threats.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.