College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China.
College of Computer Science and Technology, Nanjing University of Aeronautics and Astronautics, Nanjing, 211106, China.
Neural Netw. 2024 Apr;172:106130. doi: 10.1016/j.neunet.2024.106130. Epub 2024 Jan 15.
The significant advancement in deep learning has made it feasible to extract gender from faces accurately. However, such unauthorized extraction would pose potential threats to individual privacy. Existing protection schemes for gender privacy have exhibited satisfactory performance. Nevertheless, they suffer from gender inference from gender-related attributes and fail to support the recovery of the original image. In this paper, we propose a novel gender privacy protection scheme that aims to enhance gender privacy while supporting reversibility. Firstly, our scheme utilizes continuously optimized adversarial perturbations to prevent gender recognition from unauthorized classifiers. Meanwhile, gender-related attributes are concealed for classifiers, which prevents the inference of gender from these attributes, thereby enhancing gender privacy. Moreover, an identity preservation constraint is added to maintain identity preservation. Secondly, reversibility is supported by a reversible image transformation, allowing the perturbations to be securely removed to losslessly recover the original face when required. Extensive experiments demonstrate the effectiveness of our scheme in gender privacy protection, identity preservation, and reversibility.
深度学习的显著进步使得从面部准确提取性别成为可能。然而，这种未经授权的提取可能会对个人隐私构成潜在威胁。现有的性别隐私保护方案已经表现出了令人满意的性能。然而，它们存在从与性别相关的属性推断性别的问题，并且不支持原始图像的恢复。在本文中，我们提出了一种新颖的性别隐私保护方案，旨在增强性别隐私的同时支持可逆性。首先，我们的方案利用不断优化的对抗性扰动来防止未经授权的分类器进行性别识别。同时，隐藏性别相关属性，防止从这些属性推断性别，从而增强性别隐私。此外，还添加了身份保持约束，以保持身份保持。其次，通过可逆图像变换支持可逆性，以便在需要时安全地去除扰动，无损地恢复原始面部。广泛的实验证明了我们的方案在性别隐私保护、身份保持和可逆性方面的有效性。
