Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2409.01900 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866916380191752192 |
|---|---|
| author | Pacheco, Alexandre De Vos, Sébastien Reina, Andreagiovanni Dorigo, Marco Strobel, Volker |
| author_facet | Pacheco, Alexandre De Vos, Sébastien Reina, Andreagiovanni Dorigo, Marco Strobel, Volker |
| contents | Federated learning is a new approach to distributed machine learning that offers potential advantages such as reducing communication requirements and distributing the costs of training algorithms. Therefore, it could hold great promise in swarm robotics applications. However, federated learning usually requires a centralized server for the aggregation of the models. In this paper, we present a proof-of-concept implementation of federated learning in a robot swarm that does not compromise decentralization. To do so, we use blockchain technology to enable our robot swarm to securely synchronize a shared model that is the aggregation of the individual models without relying on a central server. We then show that introducing a single malfunctioning robot can, however, heavily disrupt the training process. To prevent such situations, we devise protection mechanisms that are implemented through secure and tamper-proof blockchain smart contracts. Our experiments are conducted in ARGoS, a physics-based simulator for swarm robotics, using the Ethereum blockchain protocol which is executed by each simulated robot. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2409_01900 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Securing Federated Learning in Robot Swarms using Blockchain Technology Pacheco, Alexandre De Vos, Sébastien Reina, Andreagiovanni Dorigo, Marco Strobel, Volker Robotics Federated learning is a new approach to distributed machine learning that offers potential advantages such as reducing communication requirements and distributing the costs of training algorithms. Therefore, it could hold great promise in swarm robotics applications. However, federated learning usually requires a centralized server for the aggregation of the models. In this paper, we present a proof-of-concept implementation of federated learning in a robot swarm that does not compromise decentralization. To do so, we use blockchain technology to enable our robot swarm to securely synchronize a shared model that is the aggregation of the individual models without relying on a central server. We then show that introducing a single malfunctioning robot can, however, heavily disrupt the training process. To prevent such situations, we devise protection mechanisms that are implemented through secure and tamper-proof blockchain smart contracts. Our experiments are conducted in ARGoS, a physics-based simulator for swarm robotics, using the Ethereum blockchain protocol which is executed by each simulated robot. |
| title | Securing Federated Learning in Robot Swarms using Blockchain Technology |
| topic | Robotics |
| url | https://arxiv.org/abs/2409.01900 |