CAREER: A Trustworthy and Verifiable Software Backplane for the Cloud Edge

职业：值得信赖且可验证的云边缘软件背板

• 批准号: 1846102
• 负责人: Felix Xiaozhu Lin
• 金额: $ 47.97万
• 依托单位: Purdue University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-06-01 至 2021-04-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1846102&HistoricalAwards=false
• 关键词: CAREER; Trustworthy; Verifiable; Software; Backplane

Internet of things (IoT) produces a large influx of streaming data. The high cost and long latency in shipping raw IoT data necessitates edge processing. The objective of this project is to safeguard IoT data during edge processing. It seeks to establish a trusted data path on the edge. As the data flows through the path, the proposed edge system ensures 1) data confidentiality: IoT data is only accessible to trusted parties; 2) integrity: all the data having arrived at the edge is exactly manipulated according to the planned processing; 3) verifiability: data flows and computations on the edge are verifiable to a trusted cloud backend. The project's research thrusts will be tightly integrated with its education and outreach plan, educating students on trustworthy computing scenarios as well as stimulating the public's interests in science, technology, engineering, and math (STEM). There are plans to contribute fresh contents to curriculum; enhance student maker activities with in-situ IoT analytics; provide a summer course on IoT/Edge for local children; and, present relevant outreach at community IoT events. As IoT is revolutionizing modern society, the project aims toward more secure and efficient intelligence driven by IoT data.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（IoT）产生了大量的流数据。运输原始物联网数据的高成本和长延迟需要边缘处理。该项目的目标是在边缘处理期间保护物联网数据。它试图在边缘建立一个可信的数据路径。当数据流经路径时，所提出的边缘系统可确保1)数据保密性：物联网数据仅供可信方访问；2)完整性：所有到达边缘的数据都精确地按照计划的处理进行处理；3)可验证性：边缘的数据流和计算对于可信的云后端是可验证的。该项目的研究重点将与其教育和推广计划紧密结合，对学生进行可信计算场景的教育，并激发公众对科学、技术、工程和数学（STEM）的兴趣。计划在课程中加入新鲜的内容；通过现场物联网分析增强学生创客活动；为当地儿童提供IoT/Edge暑期课程；并在社区物联网活动中提供相关的外展服务。由于物联网正在彻底改变现代社会，该项目旨在通过物联网数据驱动更安全和高效的智能。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

Incremental perception on real time 3D data

• DOI: 10.1145/3508396.3512875
• 发表时间: 2022-03
• 期刊: Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications
• 作者: A. Sarker;F. Lin

Minimum viable device drivers for ARM trustzone

ARM trustzone 的最小可行设备驱动程序

• DOI: 10.1145/3492321.3519565
• 发表时间: 2022
• 期刊: Eurosys 2022
• 作者: Guo, Liwei;Lin, Felix Xiaozhu
• 通讯作者: Lin, Felix Xiaozhu

Hybrid mobile vision for emerging applications

• DOI: 10.1145/3508396.3512876
• 发表时间: 2022-03
• 期刊: Proceedings of the 23rd Annual International Workshop on Mobile Computing Systems and Applications
• 作者: Na Wu;F. Lin;Feng Qian;Bo Han

GPUReplay: a 50-KB GPU stack for client ML

• DOI: 10.1145/3503222.3507754
• 发表时间: 2021-05
• 期刊: Proceedings of the 27th ACM International Conference on Architectural Support for Programming Languages and Operating Systems
• 作者: Heejin Park;F. Lin