This paper adopts Arimoto's $\alpha$-Mutual Information as a tunable privacy measure, in a privacy-preserving data release setting that aims to prevent disclosing private data to adversaries. By fine-tuning the privacy metric, we demonstrate that our approach yields superior models that effectively thwart attackers across various performance dimensions. We formulate a general distortion-based mechanism that manipulates the original data to offer privacy protection. The distortion metrics are determined according to the data structure of a specific experiment. We confront the problem expressed in the formulation by employing a general adversarial deep learning framework that consists of a releaser and an adversary, trained with opposite goals. This study conducts empirical experiments on images and time-series data to verify the functionality of $\alpha$-Mutual Information. We evaluate the privacy-utility trade-off of customized models and compare them to mutual information as the baseline measure. Finally, we analyze the consequence of an attacker's access to side information about private data and witness that adapting the privacy measure results in a more refined model than the state-of-the-art in terms of resiliency against side information.

翻译：本文采用Arimoto的$α$-互信息作为可调隐私度量，应用于旨在防止私有数据泄露给对手的隐私保护数据发布场景。通过精细调整隐私度量，我们证明所提出的方法能在多个性能维度上有效抵御攻击者。我们设计了一种通用的基于失真的机制，通过操控原始数据提供隐私保护，失真度量根据具体实验的数据结构确定。通过采用由发布者和对手组成的通用对抗深度学习框架（两者以相反目标训练），我们解决了该表述中的问题。本研究在图像和时间序列数据上开展实证实验，验证了$α$-互信息的功能性。我们评估了定制模型的隐私-效用权衡，并将其与作为基线的互信息度量进行比较。最后，我们分析了攻击者获取私有数据侧信息的影响，并观察到在抵御侧信息方面，采用该隐私度量所得到的模型比现有最优模型更具鲁棒性。