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.
Highlights
Around the world, there are about 10 billion Internet of Things (IoT) devices with increasingly advanced computing, communication, and sensors capabilities currently [1].Coupled with the rapid development of deep learning, it opens up endless possibilities for many applications, such as in vehicular networks and for industrial purposes
This paper proposes a dynamic asynchronous algorithm considering the averaging frequency control and parameter selection for federated learning to speed up model averaging
This paper proposes a novel local reliability mutual evaluation mechanism to enhance the security of poisoning attacks, where each parameter is evaluated over the local data of other parties
Summary
There are about 10 billion Internet of Things (IoT) devices with increasingly advanced computing, communication, and sensors capabilities currently [1]. This paper proposes a dynamic asynchronous algorithm considering the averaging frequency control and parameter selection for federated learning to speed up model averaging. The proposed algorithm enables federated learning to adaptively remove the stragglers with low computing power, bad channel conditions Another limitation is vulnerability to poisoning attacks. This paper proposes a novel local reliability mutual evaluation mechanism to enhance the security of poisoning attacks, where each parameter is evaluated over the local data of other parties. The main contributions of this paper are as the following: We propose a dynamic asynchronous anti poisoning federated deep learning framework to pursue both the efficiency and security of defending against poisoning attacks. The proposed mechanism enables federated learning to detect the anomalous parameter of poisoning attacks and adjust the weight proportion of model aggregation based on the evaluation result.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have