On Vehicular Data Aggregation in Federated Learning

Abstract

Vehicular federated learning systems will be beneficial to predicting traffic events in future intelligent cities. However, they might leak private information upon model updates. Hence, an honest but curious server could infer private information, such as the route of a vehicle. In this study, we elaborate on the nature of such privacy leakage caused by gradient sharing. With a simulated scenario, we focus on determining who is in danger of privacy threats and how successful a route inference attack can be. Results indicate that vanilla federated learning exposes intra-city and commuter traffic to successful location inference attacks. We also found that an adversarial aggregator server successfully infers the moving time of vehicles traveling during low-traffic periods.