Collaborative Research: SaTC: CORE: Small: UAV-NetSAFE.COM: UAV Network Security Assessment and Fidelity Enhancement through Cyber-Attack-Ready Optimized Machine-Learning Platforms

协作研究：SaTC：核心：小型：UAV-NetSAFE.COM：通过网络攻击就绪的优化机器学习平台进行无人机网络安全评估和保真度增强

• 批准号: 2006662
• 负责人: Khair Al Shamaileh
• 金额: $ 20万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2020
• 资助国家: 美国
• 起止时间: 2020-10-01 至 2024-09-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2006662&HistoricalAwards=false
• 关键词: Collaborative; Research; SaTC; CORE; Small

Unmanned aerial vehicles (UAVs) find widespread uses in civil, healthcare, and other scientific applications, such as climate monitoring, disaster and pandemic management, merchandise delivery, search and rescue operations, and space exploration. The project UAV-NetSAFE.COM promotes cyber-awareness of UAV networks, pioneers innovative security solutions, and serves the US national interest by directly mitigating the severity of cyber-attacks that could otherwise lead to human causalities, leakage of sensitive data, and degraded quality-of-service. This collaborative project promotes science advancement by investigating a multilayer security framework for the prevention, detection, and mitigation of UAV-oriented cyber-attacks. Also, this project will also impact other areas of high societal interest, such as Internet-of-Things and smart grids. It supports broader education in the areas of cyber-security, machine-learning, and UAV networks by engaging students in educational and research activities such as developing cyber-attack models, evaluating cyber-attacks using machine learning, and designing hardware as well as software solutions for trustworthy networking. Every year, the outcomes of this project will be integrated into existing and new curricula and showcased to attract high school students into STEM degrees. Led by a female lead PI from UND, this collaborative project's educational activities and interdisciplinary research endeavors will benefit Native American students from the state of North Dakota and economically disadvantaged minority and underrepresented students from Chicago metropolitan and NW Indiana. This project is jointly funded by Secure and Trustworthy Cyberspace Program and the Established Program to Stimulate Competitive Research (EPSCoR). The overarching goal of this NSF SaTC collaborative project is to investigate the impacts of cyber-attacks on UAV networks and pioneer cyber-attack-ready platforms. From a software perspective, UAV networks' cyber-attack models will be derived to facilitate UAV-distinctive datasets that aid in the comprehensive assessment and aftermath evaluation of cyber-attack impacts on UAV networks employing qualitative risk investigations and quantitative measures. The resulting datasets will be used to empower UAV networks with both attack detection and decision-making protocols for a range of cyber-attacks by adopting advanced probabilistic and statistical machine-learning algorithms. From a hardware perspective, the PIs will explore software-defined radio setups that intertwine radio frequency beamforming circuit modules with software-based localization and path rescheduling techniques while considering practical constraints such as size and structural complexity. Therefore, the project's key contribution is to pioneer a unified framework that entails cyber-attack evaluation, detection, and countermeasures of software and hardware setups. The PIs will maintain an all-inclusive project website that will help easily disseminate the datasets of cyber-attack models and countermeasure methods to industry and research community to ensure that the proposed framework promotes UAV communication and network security. This project is jointly funded by Secure and Trustworthy Cyberspace 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.

无人驾驶飞行器（uav）广泛用于民用、医疗保健和其他科学应用，如气候监测、灾害和流行病管理、商品交付、搜索和救援行动以及空间探索。UAV- netsafe.com项目促进了无人机网络的网络意识，开创了创新的安全解决方案，并通过直接减轻可能导致人员伤亡、敏感数据泄露和服务质量下降的网络攻击的严重程度，服务于美国国家利益。该合作项目通过研究用于预防、检测和缓解面向无人机的网络攻击的多层安全框架，促进了科学进步。此外，该项目还将影响其他社会高度关注的领域，如物联网和智能电网。它通过让学生参与教育和研究活动，如开发网络攻击模型，使用机器学习评估网络攻击，以及为可信网络设计硬件和软件解决方案，支持网络安全，机器学习和无人机网络领域的更广泛教育。每年，该项目的成果将被整合到现有和新的课程中，并进行展示，以吸引高中生攻读STEM学位。该合作项目的教育活动和跨学科研究努力将惠及来自北达科他州的美国原住民学生，以及来自芝加哥大都会和西北印第安纳州的经济弱势少数民族和代表性不足的学生。该项目由安全和可信网络空间计划和促进竞争研究的既定计划（EPSCoR）共同资助。这项NSF - SaTC合作项目的总体目标是研究网络攻击对无人机网络和先锋网络攻击准备平台的影响。从软件角度来看，将推导无人机网络的网络攻击模型，以促进无人机独特的数据集，这些数据集有助于通过定性风险调查和定量措施对无人机网络的网络攻击影响进行综合评估和后果评估。由此产生的数据集将通过采用先进的概率和统计机器学习算法，为无人机网络提供攻击检测和决策协议，以应对一系列网络攻击。从硬件的角度来看，pi将探索软件定义的无线电设置，将射频波束形成电路模块与基于软件的定位和路径重新调度技术交织在一起，同时考虑尺寸和结构复杂性等实际限制。因此，该项目的关键贡献是开创了一个统一的框架，该框架涉及软件和硬件设置的网络攻击评估、检测和对策。pi将维护一个全面的项目网站，这将有助于向工业界和研究界轻松传播网络攻击模型和对策方法的数据集，以确保拟议的框架促进无人机通信和网络安全。该项目由安全和可信网络空间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。

项目成果

A Machine Learning Approach for Detecting and Classifying Jamming Attacks Against OFDM-based UAVs

• DOI: 10.1145/3468218.3469049
• 发表时间: 2021-06
• 期刊: Proceedings of the 3rd ACM Workshop on Wireless Security and Machine Learning
• 作者: Jered Pawlak;Yuchen Li;Joshua Price;M. Wright;K. Shamaileh;Quamar Niyaz;V. Devabhaktuni

Jamming Detection and Classification in OFDM-Based UAVs via Feature- and Spectrogram-Tailored Machine Learning

• DOI: 10.1109/access.2022.3150020
• 发表时间: 2022
• 期刊: IEEE Access
• 影响因子: 3.9
• 作者: Yuchen Li;Jered Pawlak;Joshua Price;K. A. Al Shamaileh;Quamar Niyaz;Sidike Paheding;V. Devabhaktuni-V.-Devabhakt

A Real-time Machine Learning-based GPS Spoofing Solution for Location-dependent UAV Applications

适用于位置相关无人机应用的基于实时机器学习的 GPS 欺骗解决方案

• DOI: 10.1109/eit57321.2023.10187344
• 发表时间: 2023
• 期刊: 2023 IEEE International Conference on Electro Information Technology (eIT
• 作者: Nayfeh, M.;Price, J.;Alkhatib, M.;Al Shamaileh, K.;Kaabouch, N.;Devabhaktuni, V.
• 通讯作者: Devabhaktuni, V.

Impact of Dataset and Model Parameters on Machine Learning Performance for the Detection of GPS Spoofing Attacks on Unmanned Aerial Vehicles

数据集和模型参数对检测无人机 GPS 欺骗攻击的机器学习性能的影响

• DOI: 10.3390/app13010383
• 发表时间: 2023
• 期刊: Applied Sciences
• 作者: Talaei Khoei, Tala;Ismail, Shereen;Shamaileh, Khair Al;Devabhaktuni, Vijay Kumar;Kaabouch, Naima
• 通讯作者: Kaabouch, Naima

A Machine Learning Approach for the Detection of Injection Attacks on ADS-B Messaging Systems

用于检测 ADS-B 消息系统注入攻击的机器学习方法

• DOI: 10.1109/icnc57223.2023.10074232
• 发表时间: 2023
• 期刊: Networking and Communications (ICNC
• 作者: Price, Joshua;Slimane, Hadjar Ould;Shamaileh, Khair Al;Devabhaktuni, Vijay;Kaabouch, Naima
• 通讯作者: Kaabouch, Naima