Collaborative Research: Research Infrastructure: CCRI:New: Data-Driven Cybersecurity Research Infrastructure for Smart Manufacturing

合作研究：研究基础设施：CCRI：新：数据驱动的智能制造网络安全研究基础设施

• 批准号: 2234972
• 负责人: Narasimha Reddy
• 金额: $ 87.1万
• 依托单位: Texas A&M Engineering Experiment Station
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-04-15 至 2026-03-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2234972&HistoricalAwards=false
• 关键词: Collaborative; Research; Infrastructure; CCRI; New

Recent advances in Internet of Things sensors, artificial intelligence, computing, and communications are enabling a more distributed manufacturing paradigm where custom products are made at the point and time of need using smart manufacturing (SM) technologies. While connectivity forms the backbone in realizing SM, it has opened new cybersecurity risks and challenges, requiring a fundamental rethink and foundational efforts to tackle these challenges. Recent National Science Foundation-sponsored workshops have underscored a compelling need for a research infrastructure that can bridge the traditional divide between manufacturing and cybersecurity professionals and foster a community of CISE experts in manufacturing cybersecurity. Creating such an infrastructure is essential to understand the cybersecurity vulnerabilities, and to develop solutions tailored to SM systems. This project envisions the creation of a vibrant CISE research community for data-driven cybersecurity for SM by launching a community research platform integrating three elements: (1) A web infrastructure that enables virtual “playgrounds” to share data, codes, resources, and tools, mostly contributed by the research community; (2) a data infrastructure for curating diverse cybersecurity datasets; and (3) a SM machine infrastructure that will leverage established national resources, including the Smart Manufacturing Innovation Platform from the Department of Energy. Taken together, this infrastructure will help CISE researchers to collaborate with the SM community –spanning academia, industry, and government– to create and share data for understanding the vulnerabilities of a network of SM machines and other components of a manufacturing enterprise, and facilitate the development of AI-driven cybersecurity innovations for SM. This infrastructure will enable CISE-relevant, data-driven research thrusts spanning five key SM system elements: (1) Cybersecurity by design; (2) compiler optimizations for SM process plans and toolpaths; (3) forensics and watermarking of SM machines; (4) protections against SM process-unique side-channels; and (5) fingerprinting and securing SM networks. The community will be able to contribute their SM equipment, relevant hardware and software components, data, and innovations to grow this networked cyber-physical platform infrastructure. Emerging manufacturing enterprises are increasingly adopting advanced sensor and AI technologies and transforming themselves into smart manufacturing systems. These smart systems can connect multiple manufacturers, designers, and businesses to efficiently meet customer demands. A SM network is noted by IBM as the largest target for cybersecurity attacks among all industry sectors. Securing such a network is a daunting task. This project aims to create an online resource consisting of web infrastructure, data, and machines to bring together professionals from the manufacturing and cybersecurity communities. This infrastructure will enhance collaborations among these communities to enable a deeper understanding of current and emerging cybersecurity threats to smart manufacturing environments and enable the development of innovations to assure cybersecurity within the smart manufacturing sector. It will particularly benefit diverse researchers, practitioners, and students from cybersecurity, AI, and manufacturing disciplines. For example, the project will leverage the Inclusive Engineering Consortium, a network of 20 Underrepresented Minority serving engineering colleges to enable broad-based impact.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.

物联网传感器、人工智能、计算和通信的最新进展正在实现更加分布式的制造范式，其中使用智能制造 (SM) 技术在需要的时间点生产定制产品。虽然互联互通是实现 SM 的支柱，但它也带来了新的网络安全风险和挑战，需要从根本上重新思考并做出基础性努力来应对这些挑战。最近由美国国家科学基金会主办的研讨会强调了对研究基础设施的迫切需求，该基础设施可以弥合制造业和网络安全专业人员之间的传统鸿沟，并培养制造业网络安全领域的 CISE 专家社区。创建这样的基础设施对于了解网络安全漏洞以及开发适合 SM 系统的解决方案至关重要。该项目设想通过启动一个集成三个要素的社区研究平台，为 SM 数据驱动的网络安全创建一个充满活力的 CISE 研究社区：(1) 一个网络基础设施，使虚拟“游乐场”能够共享数据、代码、资源和工具，主要由研究社区贡献；(2) 用于管理不同网络安全数据集的数据基础设施；(3) SM 机器基础设施 这将利用现有的国家资源，包括能源部的智能制造创新平台。总而言之，该基础设施将帮助 CISE 研究人员与跨学术界、工业界和政府的 SM 社区合作，创建和共享数据，以了解 SM 机器和制造企业其他组件网络的漏洞，并促进 AI 驱动的 SM 网络安全创新的开发。该基础设施将支持 CISE 相关、数据驱动的研究重点，涵盖五个关键的 SM 系统要素：(1) 网络安全设计； (2) SM工艺计划和刀具路径的编译器优化； (3) SM机器取证和水印； (4) 针对 SM 工艺独特的侧通道的保护； (5) 指纹识别和保护 SM 网络。社区将能够贡献他们的 SM 设备、相关硬件和软件组件、数据和创新，以发展这个网络化的网络物理平台基础设施。新兴制造企业越来越多地采用先进的传感器和人工智能技术，向智能制造系统转型。这些智能系统可以连接多个制造商、设计师和企业，以有效满足客户需求。 SM网络被IBM称为所有行业中网络安全攻击的最大目标。保护这样一个网络的安全是一项艰巨的任务。该项目旨在创建一个由网络基础设施、数据和机器组成的在线资源，以汇集来自制造和网络安全社区的专业人士。该基础设施将加强这些社区之间的合作，以便更深入地了解智能制造环境中当前和新兴的网络安全威胁，并促进创新的发展，以确保智能制造领域的网络安全。它将特别有利于网络安全、人工智能和制造学科的不同研究人员、从业者和学生。例如，该项目将利用包容性工程联盟（一个由 20 所服务于工程学院的少数族裔组成的网络）来实现广泛的影响。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力优点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

Learning digital emulators for closed architecture machine tool controllers

• DOI: 10.1016/j.jmsy.2023.05.013
• 发表时间: 2023-06
• 期刊: Journal of Manufacturing Systems
• 影响因子: 12.1
• 作者: Akash Tiwari;Yuandong Wang;K. Saleeby;A. N. Reddy;S. Bukkapatnam

An analysis of war impact on Ukranian criticial infrastructure through network measurements

通过网络测量分析战争对乌克兰关键基础设施的影响

• 发表时间: 2023
• 期刊: IFIP Network Traffic Measurement and Analysis Conference
• 作者: Singlah, Rishabh;Srinivasa, Shreyas;Reddy, Narasimha;Pedersen, Jens Myrup;Vasilomanolakis, Emmanouil;Bettari, Riccardo
• 通讯作者: Bettari, Riccardo

An Analysis of war impact on Ukranian critical infrastructure through network measurements

通过网络测量分析战争对乌克兰关键基础设施的影响

• 发表时间: 2023
• 期刊: IEEE/IFIP Network Traffic Measurement and Analysis Conference
• 作者: Singla, Rishabh;Srinivasa, Shreyas;Reddy, Narasimha;Pedersen, Jens Myrup;Vasilomanolakis, Emmanouil;Bettari, Riccardo
• 通讯作者: Bettari, Riccardo

Toward a Multidimensional Analysis of the National Vulnerability Database

• DOI: 10.1109/access.2023.3309850
• 发表时间: 2023
• 期刊: IEEE Access
• 影响因子: 3.9
• 作者: Rishabh Singla;N. Reddy;R. Bettati;Hussein Alnuweiri