Invited Paper: Enhancing Privacy in Federated Learning via Early Exit
Invited Paper: Enhancing Privacy in Federated Learning via Early Exit
复制标题
DOI：
10.1145/3584684.3597274
复制
发表时间：
2023-06
期刊：
影响因子：
--
通讯作者：
Yashuo Wu;C. Chiasserini;F. Malandrino;M. Levorato
中科院分区：
文献类型：
--
作者：
Yashuo Wu;C. Chiasserini;F. Malandrino;M. Levorato
在本文中，我们研究了深度神经网络中的早期退出机制与联邦学习背景下的隐私保护之间的相互作用。我们的主要目标是评估在学习和推理阶段早期退出对隐私的影响。通过实验，我们证明了配备早期出口的模型可以明显地提高隐私性，防止成员推理攻击。我们的研究结果表明，在神经模型中包含早期退出可以作为一种有价值的工具，在降低隐私风险的同时，保留其原始的快速推理优势。
In this paper, we investigate the interplay between early exit mechanisms 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.