Sybil-based Virtual Data Poisoning Attacks in Federated Learning
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_ | 1866909611174395904 |
|---|---|
| author | Zhu, Changxun Wu, Qilong Lyu, Lingjuan Xue, Shibei |
| author_facet | Zhu, Changxun Wu, Qilong Lyu, Lingjuan Xue, Shibei |
| contents | Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, we propose a sybil-based virtual data poisoning attack, where a malicious client generates sybil nodes to amplify the poisoning model's impact. To reduce neural network computational complexity, we develop a virtual data generation method based on gradient matching. We also design three schemes for target model acquisition, applicable to online local, online global, and offline scenarios. In simulation, our method outperforms other attack algorithms since our method can obtain a global target model under non-independent uniformly distributed data. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_09983 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Sybil-based Virtual Data Poisoning Attacks in Federated Learning Zhu, Changxun Wu, Qilong Lyu, Lingjuan Xue, Shibei Cryptography and Security Machine Learning Federated learning is vulnerable to poisoning attacks by malicious adversaries. Existing methods often involve high costs to achieve effective attacks. To address this challenge, we propose a sybil-based virtual data poisoning attack, where a malicious client generates sybil nodes to amplify the poisoning model's impact. To reduce neural network computational complexity, we develop a virtual data generation method based on gradient matching. We also design three schemes for target model acquisition, applicable to online local, online global, and offline scenarios. In simulation, our method outperforms other attack algorithms since our method can obtain a global target model under non-independent uniformly distributed data. |
| title | Sybil-based Virtual Data Poisoning Attacks in Federated Learning |
| topic | Cryptography and Security Machine Learning |
| url | https://arxiv.org/abs/2505.09983 |