Enhancing Byzantine-Resistant Aggregations with Client Embedding
Zhiyuan Zhang, Hao Zhou, Fandong Meng, Jie Zhou, Xu Sun
Abstract
Byzantine-resistant aggregations detect poisonous clients and discard them to ensure that the global model is not poisoned or attacked by malicious clients. However, these aggregations are mainly conducted on the parameter space, and the parameter distances cannot reflect the data distribution divergences between clients. Therefore, existing Byzantine-resistant aggregations cannot defend against backdoor injection by malicious attackers in federated natural language tasks. In this paper, we propose the client embedding for malicious client detection to enhance Byzantine-resistant aggregations. The distances between client embeddings are required to reflect the data distribution divergences of the corresponding clients. Experimental results validate the effectiveness of the proposed client embeddings.
BibTeX
@inproceedings{zhang-etal-2024-enhancing-byzantine,
title = "Enhancing Byzantine-Resistant Aggregations with Client Embedding",
author = "Zhang, Zhiyuan and
Zhou, Hao and
Meng, Fandong and
Zhou, Jie and
Sun, Xu",
editor = "Al-Onaizan, Yaser and
Bansal, Mohit and
Chen, Yun-Nung",
booktitle = "Findings of the Association for Computational Linguistics: EMNLP 2024",
month = nov,
year = "2024",
address = "Miami, Florida, USA",
publisher = "Association for Computational Linguistics",
url = "https://aclanthology.org/2024.findings-emnlp.339/",
doi = "10.18653/v1/2024.findings-emnlp.339",
pages = "5889--5896"
}