Generating Adversarial Examples By Makeup Attacks on Face Recognition
Zheng-An Zhu, Yun-Zhong Lu, Chen-Kuo Chiang · 2019
Deep Learning models have been developed rapidly and achieved great success in computer vision and natural language processing. In this paper, we propose to generate adversarial examples to attack well-trained face recognition models by applying makeup effect to face images. It consists of two generative adversarial networks (GANs) based subnetworks, Makeup Transfer Sub-network and Adversarial Attack Sub-network. Makeup Transfer Sub-network transfers the non-makeup face images to makeup faces. Adversarial Attack Sub-networks hides attack information within makeup effect. The generated face images make the well-trained face recognition models misclassified as dodge attack or target attack. The experimental results demonstrate that our method can generate high-quality face makeup images and achieve higher error rates on various face recognition models compared to the existing attack methods.