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

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Huang, Huaxi, Yuan, Xin, Liao, Qiyu, Wang, Dadong, Liu, Tongliang
Formato: Preprint
Publicado: 2024
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866916383057510400
author Huang, Huaxi
Yuan, Xin
Liao, Qiyu
Wang, Dadong
Liu, Tongliang
author_facet Huang, Huaxi
Yuan, Xin
Liao, Qiyu
Wang, Dadong
Liu, Tongliang
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2409_03326
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning
Huang, Huaxi
Yuan, Xin
Liao, Qiyu
Wang, Dadong
Liu, Tongliang
Computer Vision and Pattern Recognition
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.
title Enhancing User-Centric Privacy Protection: An Interactive Framework through Diffusion Models and Machine Unlearning
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2409.03326