Exploring User-level Gradient Inversion with a Diffusion Prior
Fuente:
arXiv
Saved in:
| Main Authors: | , , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912022661169152 |
|---|---|
| author | Li, Zhuohang Lowy, Andrew Liu, Jing Koike-Akino, Toshiaki Malin, Bradley Parsons, Kieran Wang, Ye |
| author_facet | Li, Zhuohang Lowy, Andrew Liu, Jing Koike-Akino, Toshiaki Malin, Bradley Parsons, Kieran Wang, Ye |
| contents | We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstruction. Motivated by the low reconstruction quality of existing methods, we propose a novel gradient inversion attack that applies a denoising diffusion model as a strong image prior in order to enhance recovery in the large batch setting. Unlike traditional attacks, which aim to reconstruct individual samples and suffer at large batch and image sizes, our approach instead aims to recover a representative image that captures the sensitive shared semantic information corresponding to the underlying user. Our experiments with face images demonstrate the ability of our methods to recover realistic facial images along with private user attributes. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_07291 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Exploring User-level Gradient Inversion with a Diffusion Prior Li, Zhuohang Lowy, Andrew Liu, Jing Koike-Akino, Toshiaki Malin, Bradley Parsons, Kieran Wang, Ye Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition We explore user-level gradient inversion as a new attack surface in distributed learning. We first investigate existing attacks on their ability to make inferences about private information beyond training data reconstruction. Motivated by the low reconstruction quality of existing methods, we propose a novel gradient inversion attack that applies a denoising diffusion model as a strong image prior in order to enhance recovery in the large batch setting. Unlike traditional attacks, which aim to reconstruct individual samples and suffer at large batch and image sizes, our approach instead aims to recover a representative image that captures the sensitive shared semantic information corresponding to the underlying user. Our experiments with face images demonstrate the ability of our methods to recover realistic facial images along with private user attributes. |
| title | Exploring User-level Gradient Inversion with a Diffusion Prior |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2409.07291 |