A deep learning model usually has to sacrifice some utilities when it acquires some other abilities or characteristics. Privacy preservation has such trade-off relationships with utilities. The loss disparity between various defense approaches implies the potential to decouple generalizability and privacy risks to maximize privacy gain. In this paper, we identify that the model's generalization and privacy risks exist in different regions in deep neural network architectures. Based on the observations that we investigate, we propose Privacy-Preserving Training Principle (PPTP) to protect model components from privacy risks while minimizing the loss in generalizability. Through extensive evaluations, our approach shows significantly better maintenance in model generalizability while enhancing privacy preservation.

翻译：深度学习模型在获得某些能力或特性时通常需要牺牲部分效用。隐私保护与模型效用之间便存在此类权衡关系。不同防御方法间的损失差异表明，存在通过解耦泛化性与隐私风险以最大化隐私收益的潜力。本文研究发现，深度神经网络架构中模型的泛化风险与隐私风险存在于不同区域。基于系统观察，我们提出隐私保护训练原则（PPTP），在最小化泛化性损失的同时保护模型组件免受隐私风险侵害。通过大量评估验证，本方法在增强隐私保护的同时，显著更好地保持了模型的泛化性能。