Multi-Trigger-Key: Towards Multi-Task Privacy Preserving In Deep Learning

TL;DR

This paper introduces a Multi-Trigger-Key framework for privacy-preserving multi-task deep learning, enabling secure inference by associating tasks with trigger-keys and balancing privacy with model accuracy.

Contribution

The novel MTK framework securely associates each task with a trigger-key and incorporates a decoupling training process to prevent information leakage in multi-task models.

Findings

Effective privacy protection demonstrated without significant performance loss.

Theoretical guarantees support the privacy-preserving claims.

Experimental results validate the approach across multiple tasks.

Abstract

Deep learning-based Multi-Task Classification (MTC) is widely used in applications like facial attributes and healthcare that warrant strong privacy guarantees. In this work, we aim to protect sensitive information in the inference phase of MTC and propose a novel Multi-Trigger-Key (MTK) framework to achieve the privacy-preserving objective. MTK associates each secured task in the multi-task dataset with a specifically designed trigger-key. The true information can be revealed by adding the trigger-key if the user is authorized. We obtain such an MTK model by training it with a newly generated training set. To address the information leakage malaise resulting from correlations among different tasks, we generalize the training process by incorporating an MTK decoupling process with a controllable trade-off between the protective efficacy and the model performance. Theoretical guarantees and experimental results demonstrate the effectiveness of the privacy protection without appreciable hindering on the model performance.