Human-Unrecognizable Differential Private Noised Image Generation Method.
Sensors (Basel)
; 24(10)2024 May 16.
Article
en En
| MEDLINE
| ID: mdl-38794019
ABSTRACT
Differential privacy has emerged as a practical technique for privacy-preserving deep learning. However, recent studies on privacy attacks have demonstrated vulnerabilities in the existing differential privacy implementations for deep models. While encryption-based methods offer robust security, their computational overheads are often prohibitive. To address these challenges, we propose a novel differential privacy-based image generation method. Our approach employs two distinct noise types one makes the image unrecognizable to humans, preserving privacy during transmission, while the other maintains features essential for machine learning analysis. This allows the deep learning service to provide accurate results, without compromising data privacy. We demonstrate the feasibility of our method on the CIFAR100 dataset, which offers a realistic complexity for evaluation.
Texto completo:
1
Base de datos:
MEDLINE
Idioma:
En
Revista:
Sensors (Basel)
Año:
2024
Tipo del documento:
Article