Face image de‐identification by feature space adversarial perturbation
Hanyu Xue, Bo Liu, Xin Yuan, Ming Ding, Tianqing Zhu
Abstract
Summary Privacy leakage in images attracts increasing concerns these days, as photos uploaded to large social platforms are usually not processed by proper privacy protection mechanisms. Moreover, with advanced artificial intelligence (AI) tools such as deep neural network (DNN), an adversary can detect people's identities and collect other sensitive personal information from images at an unprecedented scale. In this paper, we introduce a novel face image de‐identification framework using adversarial perturbations in the feature space. Manipulating the feature space vector ensures the good transferability of our framework. Moreover, the proposed feature space adversarial perturbation generation algorithm can successfully protect the identity‐related information while ensuring the other attributes remain similar. Finally, we conduct extensive experiments on two face image datasets to evaluate the performance of the proposed method. Our results show that the proposed method can generate real‐looking privacy‐preserving images efficiently. Although our framework has only been tested on two real‐life face image datasets, it can be easily extended to other types of images.