Collaborative Research: IMR: MM-1B: Privacy-Preserving Data Sharing for Mobile Internet Measurement and Traffic Analytics

合作研究：IMR：MM-1B：移动互联网测量和流量分析的隐私保护数据共享

• 批准号: 2319487
• 负责人: Rose Qingyang Hu
• 金额: $ 17万
• 依托单位: Utah State University
• 依托单位国家: 美国
• 项目类别: Continuing Grant
• 财政年份: 2023
• 资助国家: 美国
• 起止时间: 2023-10-01 至 2026-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2319487&HistoricalAwards=false
• 关键词: Collaborative; Research; IMR; MM; 1B

Mobile Internet measurement is critical to network design, resource allocation, and troubleshooting network issues. However, sharing of mobile Internet measurement data can potentially compromise user privacy. Given the wide introduction of artificial intelligence to mobile Internet measurement and traffic analytics, there is an urgent need for data sharing solutions that provide explainability in terms of the trade-offs among data quality, utility and quantity. To close the gap, the objective of this project is to develop new methods to augment data with explainable data quality and utility, to access and share collected data in a privacy-preserving manner, and to collaboratively analyze Internet data with intelligence and autonomy.This collaborative project brings together investigators from University of Nebraska-Lincoln, Utah State University, and University of Wisconsin-Madison. It aims to lay a solid foundation for mobile Internet measurement with privacy preservation, collaborative and distributed intelligence, and autonomy. Methodologies and methods will be developed for quality-explainable data synthesis and augmentation; privacy-preserving data sharing; and collaborative and privacy-preserving analysis of Internet measurement data. Moreover, a mobile Internet traffic generator will be developed for evaluating the proposed methods. This project can significantly advance the prior research in Internet traffic analytics, quality-explainable and privacy-preserving data processing, mobile Internet traffic analytics, distributed artificial intelligence and machine learning algorithms, optimizations, modeling, simulations, and testbed experiments. The research efforts associated with this project will greatly advance the understandings of the critical issues in the next-generation mobile Internet measurement with distributed and collaborative intelligence to provide privacy-preserving data sharing and Internet traffic analytics. The outcomes of the project can potently foster the transition of our society into data sharing with privacy and intelligent era. Research and education will be integrated in this project by introducing emerging mobile Internet measurement and privacy-preserving data processing with advanced topics such as 6G wireless systems, data augmentation, artificial intelligence and machine learning models into the current curricula in the three collaborative institutions.The project website is hosted at: cns.unl.edu/imr-ppds. The collected data, simulation codes, and publication list will be published on the project website. Copies of technical reports and accepted manuscripts will also be published on the project website. The website will be maintained during the project years, and remain accessible for least 2 years after the completion of the project.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.

移动的互联网测量对于网络设计、资源分配和网络故障排除至关重要。然而，移动的互联网测量数据的共享可能潜在地损害用户隐私。鉴于人工智能被广泛引入到移动的互联网测量和流量分析中，迫切需要数据共享解决方案，该解决方案在数据质量、效用和数量之间的权衡方面提供可解释性。为了缩小这一差距，本项目的目标是开发新的方法来增加数据，使其具有可解释的数据质量和效用，以保护隐私的方式访问和共享收集的数据，并以智能和自主的方式协作分析互联网数据。本合作项目汇集了来自内布拉斯加大学林肯分校、犹他州州立大学和威斯康星大学麦迪逊分校的研究人员。它旨在为具有隐私保护、协作和分布式智能以及自主性的移动的互联网测量奠定坚实的基础。将为质量可解释的数据综合和扩充、保护隐私的数据共享以及对互联网测量数据进行协作和保护隐私的分析制定方法和手段。此外，一个移动的互联网流量生成器将被开发用于评估所提出的方法。该项目可以显著推进互联网流量分析，质量可解释和隐私保护数据处理，移动的互联网流量分析，分布式人工智能和机器学习算法，优化，建模，模拟和测试床实验的研究。与此项目相关的研究工作将大大推进下一代移动的互联网测量的关键问题的理解与分布式和协作智能提供隐私保护的数据共享和互联网流量分析。该项目的成果可以有力地促进我们的社会向隐私和智能时代的数据共享过渡。该项目将把研究和教育结合起来，将新兴的移动的互联网测量和隐私保护数据处理以及6G无线系统、数据增强、人工智能和机器学习模型等高级主题引入三个合作机构的现有课程。该项目网站托管在：cns.unl.edu/imr-ppds。收集的数据、模拟代码和出版物清单将在项目网站上公布。技术报告和被接受的手稿的副本也将在项目网站上公布。该网站将在项目期间维护，并在项目完成后至少2年内保持可访问性。该奖项反映了NSF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。