Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Preprint |
| Published: |
2025
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2507.09602 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866912479419826176 |
|---|---|
| author | Ju, Bocheng Fan, Junchao Liu, Jiaqi Chang, Xiaolin |
| author_facet | Ju, Bocheng Fan, Junchao Liu, Jiaqi Chang, Xiaolin |
| contents | Federated learning enables collaborative machine learning while preserving data privacy. However, the rise of federated unlearning, designed to allow clients to erase their data from the global model, introduces new privacy concerns. Specifically, the gradient exchanges during the unlearning process can leak sensitive information about deleted data. In this paper, we introduce DRAGD, a novel attack that exploits gradient discrepancies before and after unlearning to reconstruct forgotten data. We also present DRAGDP, an enhanced version of DRAGD that leverages publicly available prior data to improve reconstruction accuracy, particularly for complex datasets like facial images. Extensive experiments across multiple datasets demonstrate that DRAGD and DRAGDP significantly outperform existing methods in data reconstruction.Our work highlights a critical privacy vulnerability in federated unlearning and offers a practical solution, advancing the security of federated unlearning systems in real-world applications. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_09602 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences Ju, Bocheng Fan, Junchao Liu, Jiaqi Chang, Xiaolin Machine Learning Artificial Intelligence Federated learning enables collaborative machine learning while preserving data privacy. However, the rise of federated unlearning, designed to allow clients to erase their data from the global model, introduces new privacy concerns. Specifically, the gradient exchanges during the unlearning process can leak sensitive information about deleted data. In this paper, we introduce DRAGD, a novel attack that exploits gradient discrepancies before and after unlearning to reconstruct forgotten data. We also present DRAGDP, an enhanced version of DRAGD that leverages publicly available prior data to improve reconstruction accuracy, particularly for complex datasets like facial images. Extensive experiments across multiple datasets demonstrate that DRAGD and DRAGDP significantly outperform existing methods in data reconstruction.Our work highlights a critical privacy vulnerability in federated unlearning and offers a practical solution, advancing the security of federated unlearning systems in real-world applications. |
| title | DRAGD: A Federated Unlearning Data Reconstruction Attack Based on Gradient Differences |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2507.09602 |