Enhancing Privacy in Federated Learning via Early Exit

In this paper, we investigate the interplay between early exit mech- anisms in deep neural networks and privacy preservation in the context of federated learning. Our primary objective is to assess how early exits impact privacy during the learning and inference phases. Through experiments, we demonstrate that models equipped with early exits perceivably boost privacy against membership inference attacks. Our findings suggest that the inclusion of early exits in neural models can serve as a valuable tool in mitigating privacy risks while, at the same time, retaining their original advantages of fast inference.