Collaborative Research: SaTC: CORE: Small: Critical Learning Periods Augmented Robust Federated Learning

协作研究：SaTC：核心：小型：关键学习期增强鲁棒联邦学习

• 批准号: 2315612
• 负责人: Hao Wang
• 金额: $ 20万
• 依托单位: Louisiana State University
• 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: 2023-10-01 至 2025-09-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2315612&HistoricalAwards=false
• 关键词: Collaborative; Research; SaTC; CORE; Small

Federated Learning (FL) is a distributed machine learning approach that allows multiple data owners ("clients") to collaboratively train machine learning models that benefit from each owner's data without having to share the data itself. Federated learning can improve privacy and protect restricted data, which makes it an attractive tool in sectors such as healthcare, fintech, and autonomous driving. However, federated learning is subject to critical learning (CL) periods: the initial rounds of training have an outsized impact on models' quality and robustness. CL periods may help federated learning systems improve model quality, if new methods for selecting and weighting contributions from different clients can be developed to address the causes of CL periods. However, they also present opportunities for attackers, who may be able to harness CL periods to launch more precise and impactful attacks. To better understand these opportunities and attacks, this project will conduct a comprehensive analysis of the characteristics and exploitability of CL periods so as to advance the study of the robustness and vulnerability of federated learning. The team will develop datasets, models, algorithms, and system source code and share it with the research community, while the scientific findings will be widely disseminated as research papers, technical reports, book chapters, course materials, and tutorials. Undergraduate students, particularly those from under-represented groups, will be engaged in the proposed research activities. The central goal of this project is to investigate and understand CL periods during the FL training process, exploiting unique properties of CL periods to enhance FL security and robustness while uncovering vulnerabilities that attackers could exploit. To achieve this objective, the project investigates three main themes. The first theme focuses on how to efficiently identify CL periods and related vulnerabilities in a timely manner during FL training. The second theme focuses on how to optimize FL model accuracy with CL periods awareness, focusing on methods for adaptive client selection that are tuned to the causes of CL periods developed in the first theme. The third theme investigates ways to generalize the findings from Theme 1 to other popular FL techniques such as gradient compression, fair aggregation, personalization, and their joint effect, to address system heterogeneity (e.g., communication bandwidth differences, heterogeneous local models, and fairness concerns). Concurrently with the three main themes, the team will also design and develop a robust FL testbed to empirically evaluate the proposed algorithms with real-world models and datasets.This project is jointly funded by Secure and Trustworthy Cyberspace 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.

联合学习（FL）是一种分布式机器学习方法，允许多个数据所有者（“客户端”）协作训练机器学习模型，这些模型从每个所有者的数据中受益，而无需共享数据本身。联合学习可以改善隐私并保护受限数据，这使其成为医疗保健，金融科技和自动驾驶等领域的一个有吸引力的工具。然而，联邦学习受到关键学习（CL）时期的影响：最初的几轮训练对模型的质量和鲁棒性有巨大的影响。CL周期可以帮助联邦学习系统提高模型质量，如果可以开发新的方法来选择和加权来自不同客户端的贡献，以解决CL周期的原因。然而，它们也为攻击者提供了机会，他们可能能够利用CL周期来发动更精确和更有影响力的攻击。为了更好地理解这些机会和攻击，本项目将对CL周期的特征和可利用性进行全面分析，以推进联邦学习鲁棒性和脆弱性的研究。该团队将开发数据集，模型，算法和系统源代码，并与研究社区共享，而科学发现将作为研究论文，技术报告，书籍章节，课程材料和教程广泛传播。本科生，特别是那些来自代表性不足的群体，将参与拟议的研究活动。该项目的中心目标是调查和了解FL训练过程中的CL周期，利用CL周期的独特属性来增强FL的安全性和鲁棒性，同时发现攻击者可能利用的漏洞。为实现这一目标，该项目调查了三个主要主题。第一个主题的重点是如何有效地识别CL期间和相关的漏洞，在FL培训及时。第二个主题的重点是如何优化FL模型的准确性与CL周期的意识，专注于自适应客户端选择的方法，调整到CL周期的原因在第一个主题中开发。第三个主题研究如何将主题1的发现推广到其他流行的FL技术，如梯度压缩，公平聚合，个性化及其联合效应，以解决系统异质性（例如，通信带宽差异、异构本地模型和公平性问题）。在讨论三个主题的同时，该研究小组还将设计和开发一个强大的FL测试平台，以便用真实世界的模型和数据集对所提出的算法进行经验性评估。该项目由安全和可信的网络空间和刺激竞争研究的既定计划（EPSCoR）共同资助该奖项反映了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进行评估，被认为值得支持审查标准。