PEAFOWL: Private Entity Alignment in Multi-Party Privacy-Preserving Machine Learning

DOI码：

10.1109/TIFS.2025.3542244

发表刊物：

IEEE Transactions on Information Forensics and Security

关键字：

Protocols,Training,Servers,Insurance,Costs, Termination of employment,Machine learning, Vectors,Hospitals,Faces

摘要：

In privacy-preserving machine learning with vertically distributed data, private entity alignment methods are used to securely match and utilize features of the same samples. However, existing methods not only risk exposing sample intersections and introducing unnecessary samples but also face a gap in adapting to multi-party scenarios. To address these limitations, we propose Peafowl, a novel multi-party private entity alignment protocol. Peafowl achieves entity alignment among multiple parties through a mapping from original datasets to intersections, termed permutation. This method mitigates intersection disclosure and sample redundancy concerns by avoiding direct use of the intersection. The proposed protocol leverages a cloud server that utilizes secret-shared shuffle to protect the privacy of the permutation, in case of colluding data providers reconstructing intersections. Further, by integrating a seed homomorphic pseudorandom generator, Peafowl avoids the intensive communication of secret sharing and achieves superior runtime performance. Additionally, an offline/online variant is introduced to ensure a linear growth in communication and computation complexity relative to the dataset size by pre-computing permutation calculations. Implemented on a real PPML framework, the protocol demonstrates practical efficiency in various multi-party settings. Experimental results indicate that Peafowl’s overhead is less than 1% of the total training cost, while the offline/online variant achieves approximately a 50% reduction in online runtime. Overall, Peafowl offers an efficient and straightforward solution for multi-party PPML, making it an attractive option for implementation and future improvements.

合写作者：

Huanghao Deng, Zukun Zhu, Xiaofeng Chen, Yuxin Xie, Pei Duan

第一作者：

Ying Gao

论文类型：

期刊论文

卷号：

20

页面范围：

2706-2720

ISSN号：

1556-6013

是否译文：

否

发表时间：

2025-02-14