arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2008.06170cs.CRcs.LG
收藏

基于树模型的隐私保护垂直联邦学习

Privacy Preserving Vertical Federated Learning for Tree-based Models

National University of Singapore(新加坡国立大学);Zhejiang University(浙江大学)

Yuncheng Wu, Shaofeng Cai, Xiaokui Xiao, Gang Chen, Beng Chin Ooi

摘要:

联邦学习(FL)是一种新兴的范例,它使多个组织能够联合训练模型,而不会相互泄露他们的私有数据。本文研究了{ \it vertical}联邦学习,它解决了以下场景:(i)协作组织拥有同一组用户的数据,但具有不相交的特征,以及(ii)只有一个组织拥有标签。我们提出了Pivot,这是一种用于隐私保护垂直决策树训练和预测的新解决方案,确保除了客户端同意发布的信息(即,最终的树模型和预测输出)。Pivot不依赖于任何受信任的第三方,并提供保护,以抵御可能危及$m$客户端的$m-1$的半诚实对手。我们进一步确定了两个隐私泄漏时,训练的决策树模型以明文形式发布,并提出了一个增强的协议,以减轻他们。所提出的解决方案还可以扩展到树集成模型,例如,随机森林(RF)和梯度提升决策树(GBDT),将单个决策树视为构建块。理论和实验分析表明,Pivot是有效的隐私实现。

英文摘要:

Federated learning (FL) is an emerging paradigm that enables multiple organizations to jointly train a model without revealing their private data to each other. This paper studies {\it vertical} federated learning, which tackles the scenarios where (i) collaborating organizations own data of the same set of users but with disjoint features, and (ii) only one organization holds the labels. We propose Pivot, a novel solution for privacy preserving vertical decision tree training and prediction, ensuring that no intermediate information is disclosed other than those the clients have agreed to release (i.e., the final tree model and the prediction output). Pivot does not rely on any trusted third party and provides protection against a semi-honest adversary that may compromise $m-1$ out of $m$ clients. We further identify two privacy leakages when the trained decision tree model is released in plaintext and propose an enhanced protocol to mitigate them. The proposed solution can also be extended to tree ensemble models, e.g., random forest (RF) and gradient boosting decision tree (GBDT) by treating single decision trees as building blocks. Theoretical and experimental analysis suggest that Pivot is efficient for the privacy achieved.

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。

↑