【Author】
Chen, Zunming; Cui, Hongyan; Wu, Ensen; Yu, Xi
【Abstract】As promising privacy-preserving machine learning technology, federated learning enables multiple clients to train the joint global model via sharing model parameters. However, inefficiency and vulnerability to poisoning attacks significantly reduce federated learning performance. To solve the aforementioned issues, we propose a dynamic asynchronous anti poisoning federated deep learning framework to pursue both efficiency and security. This paper proposes a lightweight dynamic asynchronous algorithm considering the averaging frequency control and parameter selection for federated learning to speed up model averaging and improve efficiency, which enables federated learning to adaptively remove the stragglers with low computing power, bad channel conditions, or anomalous parameters. In addition, a novel local reliability mutual evaluation mechanism is presented to enhance the security of poisoning attacks, which enables federated learning to detect the anomalous parameter of poisoning attacks and adjust the weight proportion of in model aggregation based on evaluation score. The experiment results on three datasets illustrate that our design can reduce the training time by 30% and is robust to the representative poisoning attacks significantly, confirming the applicability of our scheme.
【Keywords】federated machine learning; security; privacy-preserving; asynchronous; poisoning attack
【标题】动态异步抗毒联邦深度学习与基于区块链的信誉感知解决方案
【摘要】作为有前途的隐私保护机器学习技术，联邦学习使多个客户端能够通过共享模型参数来训练联合全局模型。然而，低效率和易受中毒攻击的脆弱性显着降低了联邦学习的性能。为了解决上述问题，我们提出了一种动态异步反中毒联合深度学习框架，以追求效率和安全性。本文提出了一种考虑平均频率控制和参数选择的轻量级动态异步算法，用于联邦学习以加快模型平均速度并提高效率，使联邦学习能够自适应地去除计算能力低、信道条件差或参数异常的落后者。此外，为了增强中毒攻击的安全性，提出了一种新的局部可靠性相互评估机制，使联邦学习能够检测到中毒攻击的异常参数，并根据评估分数调整模型聚合中的权重比例。在三个数据集上的实验结果表明，我们的设计可以减少 30% 的训练时间，并且对典型的中毒攻击具有显着的鲁棒性，证实了我们方案的适用性。
【关键词】联合机器学习；安全;隐私保护；异步;中毒发作
评论