Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2024
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866916365784317952 |
|---|---|
| author | Wang, Zifan Zhang, Binghui Pang, Meng Hong, Yuan Wang, Binghui |
| author_facet | Wang, Zifan Zhang, Binghui Pang, Meng Hong, Yuan Wang, Binghui |
| contents | Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy. Unfortunately, recent works show FL algorithms are vulnerable to the serious data reconstruction attacks. However, existing works lack a theoretical foundation on to what extent the devices' data can be reconstructed and the effectiveness of these attacks cannot be compared fairly due to their unstable performance. To address this deficiency, we propose a theoretical framework to understand data reconstruction attacks to FL. Our framework involves bounding the data reconstruction error and an attack's error bound reflects its inherent attack effectiveness. Under the framework, we can theoretically compare the effectiveness of existing attacks. For instance, our results on multiple datasets validate that the iDLG attack inherently outperforms the DLG attack. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2408_12119 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective Wang, Zifan Zhang, Binghui Pang, Meng Hong, Yuan Wang, Binghui Cryptography and Security Artificial Intelligence Federated learning (FL) is an emerging collaborative learning paradigm that aims to protect data privacy. Unfortunately, recent works show FL algorithms are vulnerable to the serious data reconstruction attacks. However, existing works lack a theoretical foundation on to what extent the devices' data can be reconstructed and the effectiveness of these attacks cannot be compared fairly due to their unstable performance. To address this deficiency, we propose a theoretical framework to understand data reconstruction attacks to FL. Our framework involves bounding the data reconstruction error and an attack's error bound reflects its inherent attack effectiveness. Under the framework, we can theoretically compare the effectiveness of existing attacks. For instance, our results on multiple datasets validate that the iDLG attack inherently outperforms the DLG attack. |
| title | Understanding Data Reconstruction Leakage in Federated Learning from a Theoretical Perspective |
| topic | Cryptography and Security Artificial Intelligence |
| url | https://arxiv.org/abs/2408.12119 |