arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2206.03396cs.LGcs.AIcs.CR
收藏

个性化联邦学习的组隐私

Group privacy for personalized federated learning

Scuola Normale Superiore(比萨高等师范学校);INRIA(法国国家信息与自动化研究所);École Polytechnique(巴黎综合理工学院);Scuola Superiore Sant’Anna(圣安娜高等学校)

Filippo Galli, Sayan Biswas, Kangsoo Jung, Tommaso Cucinotta, Catuscia Palamidessi

摘要:

联邦学习(FL)是一种协作式机器学习,其中参与的对等体/客户端在本地处理其数据,仅共享对协作模型的更新。这使得能够构建隐私感知的分布式机器学习模型等。目标是通过最小化由一组客户端本地存储的数据集集合的成本函数来优化统计模型的参数。这个过程暴露给客户端两个问题:隐私信息的泄漏和缺乏个性化的模型。另一方面,随着最近各种数据分析技术的进步,人们对参与客户端的隐私侵犯的担忧激增。为了缓解这种情况,差分隐私及其变体作为提供正式隐私保证的标准。通常,客户端代表非常异构的社区,并持有非常多样化的数据。因此,与FL社区最近关注的为代表其多样性的用户构建个性化模型框架相一致,保护客户的敏感和个人信息免受潜在威胁也至关重要。为了实现这一目标,我们考虑$d$ -隐私,也被称为度量隐私,这是本地差分隐私的变体,使用基于度量的混淆技术,保留了原始数据的拓扑分布。为了解决保护客户隐私和允许个性化模型训练以增强系统的公平性和实用性的问题,我们提出了一种利用$d$的一些关键属性来提供组隐私保证的方法。隐私,使个性化模型的框架下的FL。我们提供了理论的适用性和实验验证的真实数据集上说明的工作,我们的方法

英文摘要:

Federated learning (FL) is a type of collaborative machine learning where participating peers/clients process their data locally, sharing only updates to the collaborative model. This enables to build privacy-aware distributed machine learning models, among others. The goal is the optimization of a statistical model's parameters by minimizing a cost function of a collection of datasets which are stored locally by a set of clients. This process exposes the clients to two issues: leakage of private information and lack of personalization of the model. On the other hand, with the recent advancements in various techniques to analyze data, there is a surge of concern for the privacy violation of the participating clients. To mitigate this, differential privacy and its variants serve as a standard for providing formal privacy guarantees. Often the clients represent very heterogeneous communities and hold data which are very diverse. Therefore, aligned with the recent focus of the FL community to build a framework of personalized models for the users representing their diversity, it is also of utmost importance to protect the clients' sensitive and personal information against potential threats. To address this goal we consider $d$-privacy, also known as metric privacy, which is a variant of local differential privacy, using a a metric-based obfuscation technique that preserves the topological distribution of the original data. To cope with the issue of protecting the privacy of the clients and allowing for personalized model training to enhance the fairness and utility of the system, we propose a method to provide group privacy guarantees exploiting some key properties of $d$-privacy which enables personalized models under the framework of FL. We provide theoretical justifications to the applicability and experimental validation on real datasets to illustrate the working of our method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑