Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks
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_ | 1866929419414667264 |
|---|---|
| author | Zheng, Lele Cao, Yang Jiang, Renhe Taura, Kenjiro Shen, Yulong Li, Sheng Yoshikawa, Masatoshi |
| author_facet | Zheng, Lele Cao, Yang Jiang, Renhe Taura, Kenjiro Shen, Yulong Li, Sheng Yoshikawa, Masatoshi |
| contents | Spatiotemporal federated learning has recently raised intensive studies due to its ability to train valuable models with only shared gradients in various location-based services. On the other hand, recent studies have shown that shared gradients may be subject to gradient inversion attacks (GIA) on images or texts. However, so far there has not been any systematic study of the gradient inversion attacks in spatiotemporal federated learning. In this paper, we explore the gradient attack problem in spatiotemporal federated learning from attack and defense perspectives. To understand privacy risks in spatiotemporal federated learning, we first propose Spatiotemporal Gradient Inversion Attack (ST-GIA), a gradient attack algorithm tailored to spatiotemporal data that successfully reconstructs the original location from gradients. Furthermore, we design an adaptive defense strategy to mitigate gradient inversion attacks in spatiotemporal federated learning. By dynamically adjusting the perturbation levels, we can offer tailored protection for varying rounds of training data, thereby achieving a better trade-off between privacy and utility than current state-of-the-art methods. Through intensive experimental analysis on three real-world datasets, we reveal that the proposed defense strategy can well preserve the utility of spatiotemporal federated learning with effective security protection. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2407_08529 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks Zheng, Lele Cao, Yang Jiang, Renhe Taura, Kenjiro Shen, Yulong Li, Sheng Yoshikawa, Masatoshi Cryptography and Security Spatiotemporal federated learning has recently raised intensive studies due to its ability to train valuable models with only shared gradients in various location-based services. On the other hand, recent studies have shown that shared gradients may be subject to gradient inversion attacks (GIA) on images or texts. However, so far there has not been any systematic study of the gradient inversion attacks in spatiotemporal federated learning. In this paper, we explore the gradient attack problem in spatiotemporal federated learning from attack and defense perspectives. To understand privacy risks in spatiotemporal federated learning, we first propose Spatiotemporal Gradient Inversion Attack (ST-GIA), a gradient attack algorithm tailored to spatiotemporal data that successfully reconstructs the original location from gradients. Furthermore, we design an adaptive defense strategy to mitigate gradient inversion attacks in spatiotemporal federated learning. By dynamically adjusting the perturbation levels, we can offer tailored protection for varying rounds of training data, thereby achieving a better trade-off between privacy and utility than current state-of-the-art methods. Through intensive experimental analysis on three real-world datasets, we reveal that the proposed defense strategy can well preserve the utility of spatiotemporal federated learning with effective security protection. |
| title | Enhancing Privacy of Spatiotemporal Federated Learning against Gradient Inversion Attacks |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2407.08529 |