Privacy protection generalization with adversarial fusion

Abstract

<abstract> <p>Several biometric privacy-enhancing techniques have been appraised to protect face image privacy. However, a face privacy protection algorithm is usually designed for a specific face recognition algorithm. When the structure or threshold of the face recognition algorithm is fine-tuned, the protection algorithm may be invalid. It will cause the network bloated and make the image distortion target multiple FRAs through the existing technology simultaneously. To address this problem, a fusion technology is developed to cope with the changeable face recognition algorithms via an image perturbation method. The image perturbation is performed by using a GAN-improved algorithm including generator, nozzles and validator, referred to as the Adversarial Fusion algorithm. A nozzle structure is proposed to replace the discriminator. Paralleling multiple face recognition algorithms on the nozzle can improve the compatibility of the generated image. Next, a validator is added to the training network, which takes part in the inverse back coupling of the generator. This component can make the generated graphics have no impact on human vision. Furthermore, the group hunting theory is quoted to make the network stable and up to 4.8 times faster than other models in training. The experimental results show that the Adversarial Fusion algorithm can not only change the image feature distribution by over 42% but also deal with at least 5 commercial face recognition algorithms at the same time.</p> </abstract>