Filters








4 Hits in 1.7 sec

FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping [article]

Xiaoyu Cao, Minghong Fang, Jia Liu, Neil Zhenqiang Gong
2022 arXiv   pre-print
In this work, we bridge the gap via proposing FLTrust, a new federated learning method in which the service provider itself bootstraps trust.  ...  Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious.  ...  In this work, we bridge the gap via proposing FLTrust, a new federated learning method in which the service provider itself bootstraps trust.  ... 
arXiv:2012.13995v3 fatcat:7xgtvkwsgrhh3fualpykw7re54

FLTrust: Byzantine-robust Federated Learning via Trust Bootstrapping

Xiaoyu Cao, Minghong Fang, Jia Liu, Neil Zhenqiang Gong
2021 Proceedings 2021 Network and Distributed System Security Symposium   unpublished
In this work, we bridge the gap via proposing FLTrust, a new federated learning method in which the service provider itself bootstraps trust.  ...  Byzantine-robust federated learning aims to enable a service provider to learn an accurate global model when a bounded number of clients are malicious.  ...  In this work, we bridge the gap via proposing FLTrust, a new federated learning method in which the service provider itself bootstraps trust.  ... 
doi:10.14722/ndss.2021.24434 fatcat:h5n3ivcwujalrc4bde6z2z4bs4

Byzantine-Resilient Federated Learning with Heterogeneous Data Distribution [article]

Saurav Prakash, Hanieh Hashemi, Yongqin Wang, Murali Annavaram, Salman Avestimehr
2022 arXiv   pre-print
For mitigating Byzantine behaviors in federated learning (FL), most state-of-the-art approaches, such as Bulyan, tend to leverage the similarity of updates from the benign clients.  ...  However, in federated learning (FL), data distribution across clients is typically heterogeneous.  ...  Client nodes that provide arbitrary updates are called Byzantine clients (Lamport et al., 2019) , and it is imperative to make federated learning robust to these behaviors.  ... 
arXiv:2010.07541v4 fatcat:w6ujccz5kjdxresmixh6wj2iii

A Reputation Mechanism Is All You Need: Collaborative Fairness and Adversarial Robustness in Federated Learning [article]

Xinyi Xu, Lingjuan Lyu
2021 arXiv   pre-print
In this paper, we propose a novel Robust and Fair Federated Learning (RFFL) framework to achieve collaborative fairness and adversarial robustness simultaneously via a reputation mechanism.  ...  Federated learning (FL) is an emerging practical framework for effective and scalable machine learning among multiple participants, such as end users, organizations and companies.  ...  FLTrust: Byzantine-robust federated learning via trust bootstrapping. In Proceedings of the Network and Distributed Systems Security, 2020. Fung, C., Yoon, C. J. M., and Beschastnikh, I.  ... 
arXiv:2011.10464v2 fatcat:xyej4d7sgrc53jeq22cfib2bk4