Minimum Exposure Approach for Trustworthy Vertical Federated Learning

PhD Thesis Proposal Defence


Title: "Minimum Exposure Approach for Trustworthy Vertical Federated Learning"

by

Mr. Dashan GAO


Abstract:

As artificial intelligence advances, addressing data scarcity and privacy 
concerns becomes crucial. Federated Learning (FL) offers a privacy-preserving 
framework for collaborative model training across organizations. 
Specifically, Vertical Federated Learning (VFL) faces unique challenges 
arising from vertically partitioned data among parties. This proposal 
introduces a minimum-exposure approach for trustworthy VFL, aiming to expose 
only the minimum-necessary information needed, thereby balancing 
trustworthiness objectives such as privacy, utility, robustness, and 
efficiency. By categorizing information exposure into data and model 
parameter exposure, this approach proposes guides targeted mitigation 
strategies.

First, we address intra-sample label exposure in VFL with a two-phase 
framework: offline-phase cleansing and training-phase perturbation. Our 
proposed Label Privacy Source Coding (LPSC) encodes the minimum-necessary 
label information in the offline phase. Then, we employ adversarial training 
to enhance privacy during training. Second, we further explore a more 
challenging VFL scenario with arbitrarily-aligned samples. We introduce the 
Complementary Knowledge Distillation (CKD) framework to minimizing 
intra-sample information exposure and facilitate privacy-preserving knowledge 
transfer among parties. Third, we tackle model parameter exposure in 
heterogeneous federated transfer learning by proposing a cryptobraphy-based 
framework PP-HFTL. A model integration method in PP-HFTL reduces model 
parameter exposure and allows local model inference. Extensive experiments on 
real-world datasets demonstrate the effectiveness and efficiency of our 
approaches. For future work, we aim to address inter-sample information 
exposure in VFL by proposing a secure vertical federated dataset condensation 
(VFDC) framework.


Date:                   Thursday, 21 November 2024

Time:                   10:00am - 12:00noon

Venue:                  Room 4472
                        Lifts 25/26

Committee Members:      Prof. Qiang Yang (Supervisor)
                        Prof. Kai Chen (Co-supervisor)
                        Dr. Yangqiu Song (Chairperson)
                        Dr. Qifeng Chen