DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913925538250752 |
|---|---|
| author | Liu, Bohan Xiao, Yang Ye, Ruimeng Ling, Zinan Ma, Xiaolong Hui, Bo |
| author_facet | Liu, Bohan Xiao, Yang Ye, Ruimeng Ling, Zinan Ma, Xiaolong Hui, Bo |
| contents | Distributed backdoor attacks (DBA) have shown a higher attack success rate than centralized attacks in centralized federated learning (FL). However, it has not been investigated in the decentralized FL. In this paper, we experimentally demonstrate that, while directly applying DBA to decentralized FL, the attack success rate depends on the distribution of attackers in the network architecture. Considering that the attackers can not decide their location, this paper aims to achieve a high attack success rate regardless of the attackers' location distribution. Specifically, we first design a method to detect the network by predicting the distance between any two attackers on the network. Then, based on the distance, we organize the attackers in different clusters. Lastly, we propose an algorithm to \textit{dynamically} embed local patterns decomposed from a global pattern into the different attackers in each cluster. We conduct a thorough empirical investigation and find that our method can, in benchmark datasets, outperform both centralized attacks and naive DBA in different decentralized frameworks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2501_15005 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning Liu, Bohan Xiao, Yang Ye, Ruimeng Ling, Zinan Ma, Xiaolong Hui, Bo Machine Learning Distributed backdoor attacks (DBA) have shown a higher attack success rate than centralized attacks in centralized federated learning (FL). However, it has not been investigated in the decentralized FL. In this paper, we experimentally demonstrate that, while directly applying DBA to decentralized FL, the attack success rate depends on the distribution of attackers in the network architecture. Considering that the attackers can not decide their location, this paper aims to achieve a high attack success rate regardless of the attackers' location distribution. Specifically, we first design a method to detect the network by predicting the distance between any two attackers on the network. Then, based on the distance, we organize the attackers in different clusters. Lastly, we propose an algorithm to \textit{dynamically} embed local patterns decomposed from a global pattern into the different attackers in each cluster. We conduct a thorough empirical investigation and find that our method can, in benchmark datasets, outperform both centralized attacks and naive DBA in different decentralized frameworks. |
| title | DBA-DFL: Towards Distributed Backdoor Attacks with Network Detection in Decentralized Federated Learning |
| topic | Machine Learning |
| url | https://arxiv.org/abs/2501.15005 |