Private Data Leakage in Federated Human Activity Recognition for Wearable Healthcare Devices

Wearable wristband or watch can be utilized for health monitoring, such as determining the user's activity status based on behavior and providing reasonable exercise recommendations. Obviously, the individual data perception and local computing capabilities of a single wearable device are limited, making it difficult to train a robust user behavior recognition model. Typically, joint modeling requires the collaboration of multiple wearable devices. An appropriate research approach is Federated Human Activity Recognition (HAR), which can train a global model without uploading users' local exercise data. Nevertheless, recent studies indicate that federated learning still faces serious data security and privacy issues. To the best of our knowledge, there is no existing research on membership information leakage in Federated HAR. Therefore, our study aims to investigate the joint modeling process of multiple wearable devices for user behavior recognition, with a focus on analyzing the privacy leakage issues of wearable data. In our system, we consider a federated learning architecture consisting of $N$ wearable device users and a parameter server. The parameter server distributes the initial model to each user, who independently perceives their motion sensor data, conducts local model training, and uploads it to the server. The server aggregates these local models until convergence. In the federated learning architecture, the server may be curious and seek to obtain privacy information about relevant users from the model parameters. Hence, we consider membership inference attacks based on malicious servers, which exploit differences in model generalization across different client data. Through experimentation deployed on five publicly available HAR datasets, we demonstrate that the accuracy of malicious server membership inference reaches 92\%.