MRI: Development of High-Confidence Medical Cyber-Physical System Research Instrument with Benchmark Security Software

MRI：使用基准安全软件开发高可信度医疗信息物理系统研究仪器

• 批准号: 2117785
• 负责人: Xiali Hei
• 金额: $ 113.43万
• 依托单位: University of Louisiana at Lafayette
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2117785&HistoricalAwards=false
• 关键词: MRI; Development; Confidence; Medical; Cyber

Medical cyber-physical systems (MCPS) require high reliability and security because they are safety critical. The lack of test benchmarks, suitable hardware-software interfaces, and easy-to-test hardware platforms makes it challenging to evaluate, verify, and validate the security mechanisms and reliability of high-confidence MCPS (HC-MCPS). This project aims to develop a configurable, extendable, opensource, reliable, human-in-the-loop HC-MCPS testbed. The HC-MCPS testbed will advance the ability to simulate attack/defense models. It will provide a simulation platform for cyber-physical attacks, artificial intelligence (AI) attacks, control instability detectors, and allow the researchers to conduct multidisciplinary research. The instrument will enable researchers to make medical cyber-physical systems more reliable and secure, ultimately improving the quality of healthcare. It will contribute to research, training, and teaching at the home institution in an EPSCoR state by enabling a large number of federally and state-funded projects in the areas of Computer Science, Electrical Engineering, Mechanical Engineering, Robotic Telesurgery, and Nursing. The instrument will also be used outside of the home institution to support cyber-enabled collaborative operations and data sharing among over twenty collaborators.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.

医疗网络物理系统（MCPS）需要高可靠性和安全性，因为它们是安全关键。由于缺乏测试基准、合适的软硬件接口和易于测试的硬件平台，评估、验证和验证高置信MCPS（HC-MCPS）的安全机制和可靠性具有挑战性。本项目旨在开发一个可配置、可扩展、开源、可靠、人在回路的HC-MCPS测试平台。HC-MCPS测试平台将提高模拟攻击/防御模型的能力。它将为网络物理攻击，人工智能（AI）攻击，控制不稳定探测器提供模拟平台，并允许研究人员进行多学科研究。该仪器将使研究人员能够使医疗网络物理系统更加可靠和安全，最终提高医疗质量。它将有助于研究，培训和教学在家庭机构在EPSCoR状态，使大量的联邦和州资助的项目在计算机科学，电气工程，机械工程，机器人远程手术和护理领域。 该仪器也将用于家庭机构以外，以支持网络启用的协作操作和数据共享之间的20多个collaborators.This奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

项目成果

A Small Leak Will Sink Many Ships: Vulnerabilities Related to mini-programs Permissions

• DOI: 10.1109/compsac57700.2023.00085
• 发表时间: 2022-05
• 期刊: 2023 IEEE 47th Annual Computers, Software, and Applications Conference (COMPSAC)
• 作者: Jianyi Zhang;L. Yang;Yuyang Han;Zhi Sun;Zixiao Xiang

A reliable diabetic retinopathy grading via transfer learning and ensemble learning with quadratic weighted kappa metric

• DOI: 10.1186/s12911-024-02446-x
• 发表时间: 2024-02
• 期刊: BMC medical informatics and decision making
• 影响因子: 3.5
• 作者: Sai Venkatesh Chilukoti;Liqun Shan;Vijay Srinivas Tida;A. Maida;X. Hei

Towards Adversarial Process Control on Inertial Sensor Systems with Physical Feedback Side Channels

• DOI: 10.1145/3605758.3623494
• 发表时间: 2023-11
• 期刊: Proceedings of the 5th Workshop on CPS&IoT Security and Privacy
• 作者: Yazhou Tu;Sara Rampazzi;X. Hei

Auditory Eyesight: Demystifying μs-Precision Keystroke Tracking Attacks on Unconstrained Keyboard Inputs

• 发表时间: 2023
• 作者: Yazhou Tu;Liqun Shan;Md. Imran Hossen;Sara Rampazzi;Kevin R. B. Butler;X. Hei

A First Look at the Security of EEG-based Systems and Intelligent Algorithms under Physical Signal Injections

• DOI: 10.1145/3591197.3591304
• 发表时间: 2023-07
• 期刊: Proceedings of the 2023 Secure and Trustworthy Deep Learning Systems Workshop
• 作者: Md. Imran Hossen;Yazhou Tu;X. Hei