Alipay (hangzhou) Information Technology Co., Ltd.

Weili Han

Haoqi Wu

Li Wang

Wenqiang Ruan

In an implementation, a first party or a third party updates, by adding an offset to the first fragment, two local fragments held by the local party, where the offset enables offset data obtained by performing addition on updated fragments of each party to be greater than or equal to 0. Multi-party joint computation is performed by using the two updated local fragments together with fragments held by the other two parties to obtain two overflow fragments of an overflow bit and in a second ring for performing a modulo operation on a second value of an n power of 2, m is less than n; and the overflow bit indicates whether the offset data is greater than or equal to the first value. Two converted fragments are obtained in the second ring based on the two updated local fragments, the two overflow fragments, and the offset.

Secure-fragment-conversion methods and apparatuses for protecting privacy data

Embodiments of this specification disclose secure multi-party computation for privacy protection. In an implementation, a method includes obtaining a fragment of first gradient data and a fragment of noise data, where the first gradient data is gradient data of a loss function. Based on the fragment of first gradient data by performing secure multi-party computation with another participant, obtaining a fragment of second gradient data, where the second gradient data is gradient data obtained after the first gradient data is clipped. Based on the fragment of second gradient data and the fragment of noise data, determining a fragment of third gradient data, where the third gradient data is the second gradient data with the noise data added. A fragment of a model parameter is determined based on the fragment of third gradient data.

Growing community of inventors

Hangzhou, China

Weili Han