DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems
Fuente:
arXiv
Guardado en:
| Autores principales: | , , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2025
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866915318321905664 |
|---|---|
| author | Lamri, Hithem Alam, Manaar Jiang, Haiyan Maniatakos, Michail |
| author_facet | Lamri, Hithem Alam, Manaar Jiang, Haiyan Maniatakos, Michail |
| contents | Federated Unlearning (FU) enables clients to remove the influence of specific data from a collaboratively trained shared global model, addressing regulatory requirements such as GDPR and CCPA. However, this unlearning process introduces a new privacy risk: A malicious server may exploit unlearning updates to reconstruct the data requested for removal, a form of Data Reconstruction Attack (DRA). While DRAs for machine unlearning have been studied extensively in centralized Machine Learning-as-a-Service (MLaaS) settings, their applicability to FU remains unclear due to the decentralized, client-driven nature of FU. This work presents DRAUN, the first attack framework to reconstruct unlearned data in FU systems. DRAUN targets optimization-based unlearning methods, which are widely adopted for their efficiency. We theoretically demonstrate why existing DRAs targeting machine unlearning in MLaaS fail in FU and show how DRAUN overcomes these limitations. We validate our approach through extensive experiments on four datasets and four model architectures, evaluating its performance against five popular unlearning methods, effectively demonstrating that state-of-the-art FU methods remain vulnerable to DRAs. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2506_01777 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems Lamri, Hithem Alam, Manaar Jiang, Haiyan Maniatakos, Michail Machine Learning Federated Unlearning (FU) enables clients to remove the influence of specific data from a collaboratively trained shared global model, addressing regulatory requirements such as GDPR and CCPA. However, this unlearning process introduces a new privacy risk: A malicious server may exploit unlearning updates to reconstruct the data requested for removal, a form of Data Reconstruction Attack (DRA). While DRAs for machine unlearning have been studied extensively in centralized Machine Learning-as-a-Service (MLaaS) settings, their applicability to FU remains unclear due to the decentralized, client-driven nature of FU. This work presents DRAUN, the first attack framework to reconstruct unlearned data in FU systems. DRAUN targets optimization-based unlearning methods, which are widely adopted for their efficiency. We theoretically demonstrate why existing DRAs targeting machine unlearning in MLaaS fail in FU and show how DRAUN overcomes these limitations. We validate our approach through extensive experiments on four datasets and four model architectures, evaluating its performance against five popular unlearning methods, effectively demonstrating that state-of-the-art FU methods remain vulnerable to DRAs. |
| title | DRAUN: An Algorithm-Agnostic Data Reconstruction Attack on Federated Unlearning Systems |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2506.01777 |