arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 1907.03373cs.LGcs.CRstat.ML
收藏

基于秘密向量机的隐私保护分类

Privacy-Preserving Classification with Secret Vector Machines

EPFL(洛桑联邦理工学院);Cliqz

Valentin Hartmann, Konark Modi, Josep M. Pujol, Robert West

摘要:

如今,大量有价值的数据分布在数百万用户持有的设备中,例如个人电脑、电话或物联网设备。许多公司收集这些数据的目的是将其用于训练机器学习模型,使他们能够改进服务。然而,用户持有的数据往往是敏感的,收集这些数据在隐私方面存在问题。我们通过提出一种新的方法来解决这个问题,这种方法类似于最近提出的联邦学习范式,但在更严格的隐私要求下,训练模型的服务器被认为是不可信的,并且可能是恶意的。因此,我们通过设计而不是信任来保护用户隐私。特别是,我们的框架,称为秘密向量机(SecVM),提供了一种算法,用于训练线性支持向量机(SVM)的设置中,数据持有客户端与不可信的服务器通过交换旨在不透露任何个人身份信息的消息进行通信。我们从两个方面来评估我们的模型。首先,在离线评估中,我们训练SecVM从推文中预测用户性别,这表明我们可以在不牺牲分类性能的情况下保护用户隐私。其次,我们为Cliqz Web浏览器实现了SecVM的分布式框架,并将其部署在具有数千个客户端的大规模在线评估中用于预测用户性别,大幅超过基线,从而展示了SecVM适用于生产环境。

英文摘要:

Today, large amounts of valuable data are distributed among millions of user-held devices, such as personal computers, phones, or Internet-of-things devices. Many companies collect such data with the goal of using it for training machine learning models allowing them to improve their services. User-held data is, however, often sensitive, and collecting it is problematic in terms of privacy. We address this issue by proposing a novel way of training a supervised classifier in a distributed setting akin to the recently proposed federated learning paradigm, but under the stricter privacy requirement that the server that trains the model is assumed to be untrusted and potentially malicious. We thus preserve user privacy by design, rather than by trust. In particular, our framework, called secret vector machine (SecVM), provides an algorithm for training linear support vector machines (SVM) in a setting in which data-holding clients communicate with an untrusted server by exchanging messages designed to not reveal any personally identifiable information. We evaluate our model in two ways. First, in an offline evaluation, we train SecVM to predict user gender from tweets, showing that we can preserve user privacy without sacrificing classification performance. Second, we implement SecVM's distributed framework for the Cliqz web browser and deploy it for predicting user gender in a large-scale online evaluation with thousands of clients, outperforming baselines by a large margin and thus showcasing that SecVM is suitable for production environments.

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。

↑