Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning
Fuente:
arXiv
Gespeichert in:
| Hauptverfasser: | , , , |
|---|---|
| Format: | Preprint |
| Veröffentlicht: |
2022
|
| Schlagworte: | |
| Online-Zugang: | |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| _version_ | 1866911743632998400 |
|---|---|
| author | Ozfatura, Kerem Ozfatura, Emre Kupcu, Alptekin Gunduz, Deniz |
| author_facet | Ozfatura, Kerem Ozfatura, Emre Kupcu, Alptekin Gunduz, Deniz |
| contents | The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients' models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2208_09894 |
| institution | arXiv |
| publishDate | 2022 |
| record_format | arxiv |
| spellingShingle | Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning Ozfatura, Kerem Ozfatura, Emre Kupcu, Alptekin Gunduz, Deniz Machine Learning Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing The increasing popularity of the federated learning (FL) framework due to its success in a wide range of collaborative learning tasks also induces certain security concerns. Among many vulnerabilities, the risk of Byzantine attacks is of particular concern, which refers to the possibility of malicious clients participating in the learning process. Hence, a crucial objective in FL is to neutralize the potential impact of Byzantine attacks and to ensure that the final model is trustable. It has been observed that the higher the variance among the clients' models/updates, the more space there is for Byzantine attacks to be hidden. As a consequence, by utilizing momentum, and thus, reducing the variance, it is possible to weaken the strength of known Byzantine attacks. The centered clipping (CC) framework has further shown that the momentum term from the previous iteration, besides reducing the variance, can be used as a reference point to neutralize Byzantine attacks better. In this work, we first expose vulnerabilities of the CC framework, and introduce a novel attack strategy that can circumvent the defences of CC and other robust aggregators and reduce their test accuracy up to %33 on best-case scenarios in image classification tasks. Then, we propose a new robust and fast defence mechanism that is effective against the proposed and other existing Byzantine attacks. |
| title | Byzantines can also Learn from History: Fall of Centered Clipping in Federated Learning |
| topic | Machine Learning Artificial Intelligence Cryptography and Security Distributed, Parallel, and Cluster Computing |
| url | https://arxiv.org/abs/2208.09894 |