Invention Grant
- Patent Title: Secure multi-party computation attribution
-
Application No.: US16386103Application Date: 2019-04-16
-
Publication No.: US11245536B2Publication Date: 2022-02-08
- Inventor: Andrew Knox
- Applicant: Facebook, Inc.
- Applicant Address: US CA Menlo Park
- Assignee: Facebook, Inc.
- Current Assignee: Facebook, Inc.
- Current Assignee Address: US CA Menlo Park
- Agency: Fenwick & West LLP
- Main IPC: H04L9/32
- IPC: H04L9/32 ; G06Q30/02 ; H04L29/06

Abstract:
Secure multi-party computations may be used to get attribution results without compromising user privacy. A content provider and an advertiser may each sign a calculation indicating that they wish to share data using a secure multi-party computation. A measurement company may sign the calculation indicating that the measurement company has evaluated the computation and that the computation will protect user privacy. A user device may confirm with the verification service that all parties have signed the calculation. The user device may transmit one-time identifiers to the measurement company, which allows impression data and conversion data stored by the content provider and the advertiser to be linked. The content provider, the advertiser, and the measurement company may perform the secure multi-party computation, which allows the advertiser to evaluate attribution results without accessing the user data stored by the content provider.
Public/Granted literature
- US20200336313A1 SECURE MULTI-PARTY COMPUTATION ATTRIBUTION Public/Granted day:2020-10-22
Information query