Trusted Aggregation (TAG): Model Filtering Backdoor Defense In Federated Learning

ICLR 2023(2023)

引用 0|浏览13
Federated Learning is a framework for training machine learning models from multiple local data sets without access to the data in aggregate. A shared model is jointly learned through an interactive process between server and clients that combines locally learned model gradients or weights. However, the lack of data transparency naturally raises concerns about model security. Recently, several state-of-the-art backdoor attacks have been proposed, which achieve high attack success rates while simultaneously being difficult to detect, leading to compromised federated learning models. In this paper, motivated by differences in the output layer distribution between models trained with and without the presence of backdoor attacks, we propose a defense method that can prevent backdoor attacks from influencing the model while maintaining the accuracy of the original classification task. TAG leverages a small validation data set to estimate the largest change that a benign user's local training can make to the output layer of the shared model, which can be used as a cutoff for returning user models. Experimental results on multiple data sets show that TAG defends against backdoor attacks even when 40\% of the user submissions to update the shared model are malicious.
federated learning,backdoor attack,robust aggregation
AI 理解论文
Chat Paper