基于人脸去识别的隐私保护对抗生成网络
Privacy-Protective-GAN for Privacy Preserving Face De-Identification
-
摘要: 在这个图片及影像资源迅速增长并且随处可得的时代,人脸去识别变得越来越至关重要。人脸识别技术的迅速发展,也引起了人们对隐私泄露的担忧。目前的主流人脸去识别框架,大部分是基于"k-same"算法,在有效性及生成图片质量上有待提高。在这篇文章中,我们提出隐私保护对抗生成网络(PP-GAN),结合GAN及新的验证、约束模块,设计用于在给定单帧输入时,生成去识别而保留结构相似性的输出。我们提出的方法不仅优于现有的人脸去识别技术,且提供了结合GAN和先验知识的实用框架。
目的: 通过人脸去识别来实现隐私保护,同时通过保持原始图像和生成图像的结构相似性来保留去识别图像的可用性。
创新点: 本文提出了PP-GAN来直接优化人脸去识别目标,从而生成图像质量好,去识别有效性高的图像。
方法: PP-GAN,由常规GAN,人脸验证模块和结构相似约束模块构成,通过组合优化,实现最终的去识别生成器。
结论: 我们呈现了一个新的人脸去识别框架PP-GAN,可以给定单张人脸图片,生成相应的去识别图片。我们显式地在目标函数中加入了去识别指标,从而保证了隐私保护的有效性,同时,我们希望尽可能地保持输入和生成图像的结构相似性,以最大程度地保留去识别图片的可用性。在实验部分,我们定量分析了提出算法在隐私保护,可用性保留和视觉相似性方面的有效性。Abstract: Face de-identification has become increasingly important as the image sources are explosively growing and easily accessible. The advance of new face recognition techniques also arises people's concern regarding the privacy leakage. The mainstream pipelines of face de-identification are mostly based on the k-same framework, which bears critiques of low effectiveness and poor visual quality. In this paper, we propose a new framework called Privacy-Protective-GAN (PP-GAN) that adapts GAN (generative adversarial network) with novel verificator and regulator modules specially designed for the face de-identification problem to ensure generating de-identified output with retained structure similarity according to a single input. We evaluate the proposed approach in terms of privacy protection, utility preservation, and structure similarity. Our approach not only outperforms existing face de-identification techniques but also provides a practical framework of adapting GAN with priors of domain knowledge.