Efficient Two-Party Vertical Federated Linear Model with TTP-aided Secret Sharing

The Hong Kong University of Science and Technology
Department of Computer Science and Engineering


MPhil Thesis Defence


Title: "Efficient Two-Party Vertical Federated Linear Model with TTP-aided
Secret Sharing"

By

Mr. Mingxuan FAN


Abstract:

Vertical Federated Learning (VFL) has emerged as one of the most predominant
approaches for secure collaborative machine learning where the training data is
partitioned by features among multiple parties. Most VFL algorithms primarily
rely on two fundamental privacy-preserving techniques: Homomorphic Encryption
(HE) and secure Multi-Party Computation (MPC). Though generally considered with
stronger privacy guarantees, existing general-purpose MPC frameworks suffer
from expensive computation and communication overhead and are inefficient
especially under VFL settings. This study centers around MPC-based VFL
algorithms and presents a novel approach for two-party vertical federated
linear models via an efficient secret sharing (SS) scheme with a trusted
coordinator. The proposed approach can achieve significant acceleration of the
training procedure in vertical federated linear models of between 2.5× and 6.6×
than other existing MPC frameworks under the same security setting.


Date:                   Tuesday, 14 November 2023

Time:                   10:00am - 12:00noon

Venue:                  Room 3598
                        lifts 27/28

Committee Members:      Prof. Kai Chen (Supervisor)
                        Dr. Yangqiu Song (Chairperson)
                        Dr. Shuai Wang


**** ALL are Welcome ****