Voyager: MTD-Based Aggregation Protocol for Mitigating Poisoning Attacks on DFL
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2023
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866910330372751360 |
|---|---|
| author | Feng, Chao Celdran, Alberto Huertas Vuong, Michael Bovet, Gerome Stiller, Burkhard |
| author_facet | Feng, Chao Celdran, Alberto Huertas Vuong, Michael Bovet, Gerome Stiller, Burkhard |
| contents | The growing concern over malicious attacks targeting the robustness of both Centralized and Decentralized Federated Learning (FL) necessitates novel defensive strategies. In contrast to the centralized approach, Decentralized FL (DFL) has the advantage of utilizing network topology and local dataset information, enabling the exploration of Moving Target Defense (MTD) based approaches.
This work presents a theoretical analysis of the influence of network topology on the robustness of DFL models. Drawing inspiration from these findings, a three-stage MTD-based aggregation protocol, called Voyager, is proposed to improve the robustness of DFL models against poisoning attacks by manipulating network topology connectivity. Voyager has three main components: an anomaly detector, a network topology explorer, and a connection deployer. When an abnormal model is detected in the network, the topology explorer responds strategically by forming connections with more trustworthy participants to secure the model. Experimental evaluations show that Voyager effectively mitigates various poisoning attacks without imposing significant resource and computational burdens on participants. These findings highlight the proposed reactive MTD as a potent defense mechanism in the context of DFL. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2310_08739 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | Voyager: MTD-Based Aggregation Protocol for Mitigating Poisoning Attacks on DFL Feng, Chao Celdran, Alberto Huertas Vuong, Michael Bovet, Gerome Stiller, Burkhard Cryptography and Security Distributed, Parallel, and Cluster Computing The growing concern over malicious attacks targeting the robustness of both Centralized and Decentralized Federated Learning (FL) necessitates novel defensive strategies. In contrast to the centralized approach, Decentralized FL (DFL) has the advantage of utilizing network topology and local dataset information, enabling the exploration of Moving Target Defense (MTD) based approaches. This work presents a theoretical analysis of the influence of network topology on the robustness of DFL models. Drawing inspiration from these findings, a three-stage MTD-based aggregation protocol, called Voyager, is proposed to improve the robustness of DFL models against poisoning attacks by manipulating network topology connectivity. Voyager has three main components: an anomaly detector, a network topology explorer, and a connection deployer. When an abnormal model is detected in the network, the topology explorer responds strategically by forming connections with more trustworthy participants to secure the model. Experimental evaluations show that Voyager effectively mitigates various poisoning attacks without imposing significant resource and computational burdens on participants. These findings highlight the proposed reactive MTD as a potent defense mechanism in the context of DFL. |
| title | Voyager: MTD-Based Aggregation Protocol for Mitigating Poisoning Attacks on DFL |
| topic | Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2310.08739 |