arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2107.08581cs.CVcs.AI
收藏

一种系统的人脸去身份化方案

A Systematical Solution for Face De-identification

Center for Research on Intelligent Perception and Computing(智能感知与计算研究中心);Nanjing University of Aeronautics and Astronautics(南京航空航天大学);College of Automation(自动化学院);Chinese Academy of Sciences, Institute of Automation(中国科学院自动化研究所)

Songlin Yang, Wei Wang, Yuehua Cheng, Jing Dong

摘要:

随着人脸数据中的身份信息与个人信用和财产安全的关系越来越密切,人们对人脸数据隐私的保护日益重视。在不同的任务中,人们对人脸去识别(De-ID)有不同的要求,因此我们提出了一个系统的解决方案,兼容这些De-ID操作。首先,构造一个属性解纠缠和生成网络来编码人脸的两个部分,即身份(嘴,鼻子和眼睛等面部特征)和表情(包括表情,姿态和光照)。通过人脸交换,我们可以完全删除原始ID。其次,与以往的传统对抗方法不同,我们增加了一个对抗向量映射网络来扰动人脸图像的潜在代码。通过这种方法,我们可以构造无限制的对抗图像,以降低模型识别的ID相似度。我们的方法可以灵活地去识别人脸数据的各种方式和处理后的图像具有较高的图像质量。

英文摘要:

With the identity information in face data more closely related to personal credit and property security, people pay increasing attention to the protection of face data privacy. In different tasks, people have various requirements for face de-identification (De-ID), so we propose a systematical solution compatible for these De-ID operations. Firstly, an attribute disentanglement and generative network is constructed to encode two parts of the face, which are the identity (facial features like mouth, nose and eyes) and expression (including expression, pose and illumination). Through face swapping, we can remove the original ID completely. Secondly, we add an adversarial vector mapping network to perturb the latent code of the face image, different from previous traditional adversarial methods. Through this, we can construct unrestricted adversarial image to decrease ID similarity recognized by model. Our method can flexibly de-identify the face data in various ways and the processed images have high image quality.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑