MLWiNS: Distributed Learning for the Nomadic Edge

MLWiNS：游牧边缘的分布式学习

• 批准号: 2003129
• 负责人: Suman Banerjee
• 金额: $ 59.33万
• 依托单位: University of Wisconsin-Madison
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-01-01 至 2023-12-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2003129&HistoricalAwards=false
• 关键词: MLWiNS; Distributed; Learning; Nomadic; Edge

Edge computing is a paradigm that brings computing closer to where the data is generated, such as cellular networks, internet service providers, and enterprise networks. Typical edge nodes are static and are located in fixed points over a wired network. This project creates a new notion of edge computing, Nautilus, to support distributed machine learning over mobile nodes, such as vehicles. The project aims to create new techniques that can enable a new class of applications that leverage sensors mounted on vehicles. The applications range from smart transportation, to urban planning, and to broadly support smarter cities and communities. The broader impact of this project includes: (i) creation of a hands-on curriculum centered around computer vision techniques and machine learning; (ii) educating the broader public on wireless systems and machine learning technologies and their impact on our society; (iii) engagement with industrial partners and with regulatory bodies; (iv) public dissemination of the developed source code and prototype design; (v) mentoring of women STEM students through various campus programs as well as global ones and helping them identify opportunities for fulfilling careers in this domain.This project is structured in a three-tiered architecture consisting of the nomadic edge (in vehicles), the static edge (co-located with Radio Access Networks), and the cloud. To support diverse emerging applications across domains (e.g., smart transportation, urban planning, and more broadly across different aspects of smarter communities) which can issue queries spanning large spatio-temporal regions. The research agenda includes five complementary tasks: (i) Design of distributed and dynamic computer vision from the vehicular context, which involves collaborative and federated machine learning approaches to event and object detection under diverse conditions; (ii) Design of collaborative and distributed training and inference to address high level queries which will utilize various techniques of redundant and coded computing and communication to support efficiency and scalability; (iii) Estimation and prediction of the wireless network context to infer opportunities for communication between collaborating nomadic edge nodes, as well as between the nomadic and static edges; (iv) Design for privacy and security of both data and models; and (v) Systems integration and field trials to allow for technique refinement, evaluation, and reproducibility. Through a partnership with the local transit network — Madison Metro Transit, the research team plans to use the project research results and assist them in understanding various challenges, opportunities, and optimizations in planning various transportation and transit decisions.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.

边缘计算是一种范式，它使计算更接近数据生成的地方，例如蜂窝网络，互联网服务提供商和企业网络。典型的边缘节点是静态的，并且位于有线网络上的固定点。该项目创建了边缘计算的新概念Nautilus，以支持通过移动的节点（如车辆）进行分布式机器学习。该项目旨在创建新技术，以实现利用安装在车辆上的传感器的新一类应用。应用范围从智能交通到城市规划，以及广泛支持智能城市和社区。该项目的更广泛影响包括：（一）创建以计算机视觉技术和机器学习为中心的实践课程;（二）教育更广泛的公众了解无线系统和机器学习技术及其对我们社会的影响;（三）与工业合作伙伴和监管机构合作;（四）公开传播开发的源代码和原型设计;（v）通过各种校园项目以及全球项目指导STEM女学生，帮助她们寻找在该领域实现职业生涯的机会。该项目采用三层架构，包括移动边缘（在车辆中）、静态边缘（与无线接入网络共处）和云。为了支持跨领域的各种新兴应用程序（例如，智能交通、城市规划以及更广泛地跨越智能社区的不同方面），其可以发出跨越大的时空区域的查询。研究议程包括五个互补的任务：（一）从车辆环境设计分布式和动态计算机视觉，其中涉及协作和联合机器学习方法，以在不同条件下进行事件和物体检测;（二）设计协作和分布式训练和推理，以解决高级查询，这将利用各种冗余和编码计算和通信技术来支持效率和可扩展性;（iii）估计和预测无线网络上下文，以推断协作游牧边缘节点之间以及游牧边缘和静态边缘之间的通信机会;（iv）设计数据和模型的隐私和安全性;以及（v）系统集成和现场试验，以允许技术改进、评估和再现性。通过与当地的交通网络-麦迪逊地铁交通的合作伙伴关系，研究团队计划使用项目的研究成果，并帮助他们了解各种挑战，机遇，并在规划各种交通和交通决策优化。这个奖项反映了NSF的法定使命，并已被认为是值得通过使用基金会的智力价值和更广泛的影响审查标准进行评估的支持。

项目成果

Sample Selection for Fair and Robust Training

• 发表时间: 2021-10
• 作者: Yuji Roh;Kangwook Lee;Steven Euijong Whang;Changho Suh

On the Limitations of Stochastic Pre-processing Defenses

• DOI: 10.48550/arxiv.2206.09491
• 发表时间: 2022-06
• 期刊: ArXiv
• 作者: Yue Gao;Ilia Shumailov;Kassem Fawaz;Nicolas Papernot

Towards More Robust Keyword Spotting for Voice Assistants

• 发表时间: 2022
• 期刊: Proceedings of the 36th Annual Computer Security Applications Conference
• 作者: Shimaa Ahmed;Ilia Shumailov;Nicolas Papernot;Kassem Fawaz

Unpacking Privacy Labels: A Measurement and Developer Perspective on Google's Data Safety Section

揭开隐私标签的面纱：谷歌数据安全部分的衡量和开发者视角

• DOI: 10.48550/arxiv.2306.08111
• 发表时间: 2023
• 期刊: ArXiv
• 作者: Rishabh Khandelwal;Asmit Nayak;Paul Chung;Kassem Fawaz
• 通讯作者: Kassem Fawaz

Experimental Security Analysis of Sensitive Data Access by Browser Extensions

• DOI: 10.1145/3589334.3645683
• 发表时间: 2024-05
• 期刊: Proceedings of the ACM on Web Conference 2024
• 作者: Asmit Nayak;Rishabh Khandelwal;Earlence Fernandes;Kassem Fawaz