Multi-Trigger-Key: Towards Multi-Task Privacy Preserving In Deep Learning
This work addresses privacy concerns in applications like facial attributes and healthcare, offering a novel method for multi-task settings, though it appears incremental as it builds on existing privacy-preserving techniques.
The paper tackles the problem of protecting sensitive information during the inference phase of deep learning-based multi-task classification, proposing a Multi-Trigger-Key framework that associates each task with a trigger-key to reveal true information only for authorized users, achieving privacy protection without significantly hindering model performance as demonstrated by theoretical guarantees and experiments.
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.