Blinder: End-to-end Privacy Protection in Sensing Systems via Personalized Federated Learning
This work addresses privacy protection for users of sensing systems, such as those with IMU or radio frequency data, by enabling decentralized, real-time anonymization on edge devices, though it is incremental as it builds on existing federated learning and adversarial training techniques.
The paper tackles the problem of protecting privacy in sensor data by proposing Blinder, a personalized federated learning model that anonymizes data while maintaining utility, achieving privacy loss increases of up to 4.00% and utility decreases of up to 4.24% compared to centralized state-of-the-art methods.
This paper proposes a sensor data anonymization model that is trained on decentralized data and strikes a desirable trade-off between data utility and privacy, even in heterogeneous settings where the sensor data have different underlying distributions. Our anonymization model, dubbed Blinder, is based on a variational autoencoder and one or multiple discriminator networks trained in an adversarial fashion. We use the model-agnostic meta-learning framework to adapt the anonymization model trained via federated learning to each user's data distribution. We evaluate Blinder under different settings and show that it provides end-to-end privacy protection on two IMU datasets at the cost of increasing privacy loss by up to 4.00% and decreasing data utility by up to 4.24%, compared to the state-of-the-art anonymization model trained on centralized data. We also showcase Blinder's ability to anonymize the radio frequency sensing modality. Our experiments confirm that Blinder can obscure multiple private attributes at once, and has sufficiently low power consumption and computational overhead for it to be deployed on edge devices and smartphones to perform real-time anonymization of sensor data.