In recent years, machine learning as a service (MLaaS) has brought considerable convenience to our daily lives. However, these services raise the issue of leaking users’ sensitive attributes, such as race, when provided through the cloud. The present work overcomes this issue by proposing an innovative privacy-preserving approach called privacy-preserving class overlap (PPCO), which incorporates both a Wasserstein generative adversarial network and the idea of class overlapping to obfuscate data for better resilience against the leakage of attribute-inference attacks(i.e., malicious inference on users’ sensitive attributes). Experiments show that the proposed method can be employed to enhance current state-of-the-art works and achieve superior privacy–utility trade-off. Furthermore, the proposed method is shown to be less susceptible to the influence of imbalanced classes in training data. Finally, we provide a theoretical analysis of the performance of our proposed method to give a flavour of the gap between theoretical and empirical performances.

中文翻译：

---

通过类重叠技术进行对抗训练来保护敏感属性

近年来，机器学习即服务（MLaaS）为我们的日常生活带来了极大的便利。然而，这些服务在通过云提供时会引发泄露用户敏感属性（例如种族）的问题。目前的工作通过提出一种称为隐私保护类重叠 (PPCO) 的创新隐私保护方法来克服这个问题，该方法结合了 Wasserstein 生成对抗网络和类重叠的概念来混淆数据，以更好地抵御属性泄漏。推理攻击（即恶意推理用户的敏感属性）。实验表明，所提出的方法可用于增强当前最先进的作品并实现卓越的隐私-效用权衡。此外，所提出的方法被证明不易受训练数据中不平衡类别的影响。最后，我们对我们提出的方法的性能进行了理论分析，以了解理论和实证性能之间的差距。