 |
The first HE-based protocol was PrivFL. PrivFL combined aggregation methods and additive homomorphic oriented linear regression and logistic regression to propose a secure aggregation protocol that guarantees both user data privacy and ML model privacy and provides a prediction service for users. Look at the picture below. It represents the basic idea of Regression Training. The server performs additive HE on the model 亥 to obtain E(亥) and sends E(亥) to user Pi, each user derives E(si) and ri by SLG algorithm with E(亥) and Di (data of user pi) as input such that si - ri = 企i (企i is the local gradient). The server then decrypts the received E(si) and computes the si sum for all users, followed by using the aggregation protocol to solve for ri as input and output the ri sum for all users to the server. Finally the server can then compute 企 and update 亥 after by the formula on the left of the picture where Ua is the set of users. |
IEEE/ICACT20220347 Slide.29
[Big Slide]
[YouTube]