Back to Search Start Over

Beyond Traditional Threats: A Persistent Backdoor Attack on Federated Learning

Authors :
Liu, Tao
Zhang, Yuhang
Feng, Zhu
Yang, Zhiqin
Xu, Chen
Man, Dapeng
Yang, Wu
Source :
Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(19): 21359-21367
Publication Year :
2024

Abstract

Backdoors on federated learning will be diluted by subsequent benign updates. This is reflected in the significant reduction of attack success rate as iterations increase, ultimately failing. We use a new metric to quantify the degree of this weakened backdoor effect, called attack persistence. Given that research to improve this performance has not been widely noted,we propose a Full Combination Backdoor Attack (FCBA) method. It aggregates more combined trigger information for a more complete backdoor pattern in the global model. Trained backdoored global model is more resilient to benign updates, leading to a higher attack success rate on the test set. We test on three datasets and evaluate with two models across various settings. FCBA's persistence outperforms SOTA federated learning backdoor attacks. On GTSRB, postattack 120 rounds, our attack success rate rose over 50% from baseline. The core code of our method is available at https://github.com/PhD-TaoLiu/FCBA.

Details

Database :
arXiv
Journal :
Proceedings of the AAAI Conference on Artificial Intelligence. 2024, 38(19): 21359-21367
Publication Type :
Report
Accession number :
edsarx.2404.17617
Document Type :
Working Paper