Collaborative Research: SaTC: CORE: Small: Towards Robust, Scalable, and Resilient Radio Fingerprinting

无线电指纹识别可以使用射频信号来区分无线设备，因为这种信号中携带了独特的设备硬件缺陷。无线电指纹识别是一种物理层身份验证技术，在识别单个设备（例如物联网设备）和关键任务目标（例如无人机）方面发挥着关键作用。该项目开发了新的方法，通过协同深度学习和信号处理来提高无线电指纹的鲁棒性、可扩展性和弹性。该项目解决了三个研究问题，具体而言：(1)如何提高无线电指纹识别对无线信道时间变化的鲁棒性；(2)如何消除接收机的非线性硬件缺陷；(3)如何提高无线指纹识别对白盒攻击者的弹性。该项目的研究成果将通过出版物和新的课程模块和项目传播。这将促进网络安全劳动力的发展，并扩大来自代表性不足群体的学生在计算机领域的参与。该项目由安全与可信网络空间（SaTC）计划和促进竞争研究的既定计划（EPSCoR）共同资助。该奖项反映了美国国家科学基金会的法定使命，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。

Radio fingerprinting can distinguish wireless devices using radio frequency signals, as unique device hardware imperfections are carried in such signals. Radio fingerprinting is a physical-layer authentication technique and plays a critical role in identifying individual devices (e.g., IoT devices) and mission-critical targets (e.g., Unmanned Aerial Vehicles). This project develops new methods to promote the robustness, scalability, and resilience of radio fingerprinting by synergizing deep learning and signal processing. This project addresses three research questions, specifically (1) how to improve the robustness of radio fingerprinting against temporal variations of wireless channels; (2) how to mitigate nonlinear receiver hardware imperfections; and (3) how to improve the resilience of radio fingerprinting against white-box attackers. The research outcomes of this project will be disseminated through publications and new course modules and projects. These will promote cybersecurity workforce development as well as broaden the participation of students from underrepresented groups in computing.This project is jointly funded by the Secure and Trustworthy Cyberspace (SaTC) program, and the Established Program to Stimulate Competitive Research (EPSCoR).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.