IEEE Trans Pattern Anal Mach Intell. 2021 Jun;43(6):2158-2164. doi: 10.1109/TPAMI.2020.3015420. Epub 2021 May 11.
This work proposes a novel privacy-preserving neural network feature representation to suppress the sensitive information of a learned space while maintaining the utility of the data. The new international regulation for personal data protection forces data controllers to guarantee privacy and avoid discriminative hazards while managing sensitive data of users. In our approach, privacy and discrimination are related to each other. Instead of existing approaches aimed directly at fairness improvement, the proposed feature representation enforces the privacy of selected attributes. This way fairness is not the objective, but the result of a privacy-preserving learning method. This approach guarantees that sensitive information cannot be exploited by any agent who process the output of the model, ensuring both privacy and equality of opportunity. Our method is based on an adversarial regularizer that introduces a sensitive information removal function in the learning objective. The method is evaluated on three different primary tasks (identity, attractiveness, and smiling) and three publicly available benchmarks. In addition, we present a new face annotation dataset with balanced distribution between genders and ethnic origins. The experiments demonstrate that it is possible to improve the privacy and equality of opportunity while retaining competitive performance independently of the task.
这项工作提出了一种新颖的隐私保护神经网络特征表示方法，旨在抑制学习空间中的敏感信息，同时保持数据的实用性。新的国际个人数据保护法规要求数据控制者在管理用户的敏感数据时保证隐私并避免歧视性风险。在我们的方法中，隐私和歧视是相互关联的。与直接针对公平性改进的现有方法不同，所提出的特征表示方法强制选择属性的隐私性。这样，公平性不是目标，而是隐私保护学习方法的结果。这种方法保证了敏感信息不能被处理模型输出的任何代理利用，从而确保了隐私和机会均等。我们的方法基于对抗正则化器，该正则化器在学习目标中引入了敏感信息去除函数。该方法在三个不同的主要任务（身份、吸引力和微笑）和三个公开可用的基准上进行了评估。此外，我们还提出了一个新的带有性别和种族平衡分布的人脸注释数据集。实验表明，在不依赖任务的情况下，提高隐私性和机会均等性的同时，保持竞争力是有可能的。
