Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning

TL;DR

This paper introduces an interactive framework combining diffusion models and machine unlearning to enhance privacy protection during image data sharing and model publication, allowing user-adjustable privacy levels.

Contribution

It presents a novel comprehensive privacy protection framework that integrates generative diffusion models and machine unlearning for the first time in this context.

Findings

Outperforms existing methods on facial datasets.

Balances privacy and model performance effectively.

Enables user-adjustable privacy levels.

Abstract

In the realm of multimedia data analysis, the extensive use of image datasets has escalated concerns over privacy protection within such data. Current research predominantly focuses on privacy protection either in data sharing or upon the release of trained machine learning models. Our study pioneers a comprehensive privacy protection framework that safeguards image data privacy concurrently during data sharing and model publication. We propose an interactive image privacy protection framework that utilizes generative machine learning models to modify image information at the attribute level and employs machine unlearning algorithms for the privacy preservation of model parameters. This user-interactive framework allows for adjustments in privacy protection intensity based on user feedback on generated images, striking a balance between maximal privacy safeguarding and maintaining model performance. Within this framework, we instantiate two modules: a differential privacy diffusion model for protecting attribute information in images and a feature unlearning algorithm for efficient updates of the trained model on the revised image dataset. Our approach demonstrated superiority over existing methods on facial datasets across various attribute classifications.