Although the current face de-recognition algorithm can effectively protect the user’s identity, it will change the original attributes of the image, destroy the visual effect, or change the characteristics of the image to varying degrees. Traditional methods such as pixelation and occlusion can effectively realize face de-recognition, but the processed image cannot be used for basic processing such as face statistics and expression recognition, which greatly destroys the usability of the image in the field of online new media. In order to preserve more attributes of the original image and reduce the changes of facial skin color and texture features caused by the above de-recognition algorithm’s operation on the whole facial area, this paper proposes a privacy protection model of face image based on generative adversarial network and facial feature analysis. Our model realizes face recognition based on changing the original image as little as possible. Specifically, we identify and extract features from fixed parts in face images, including eyes, nose, mouth, eyebrows, and cheeks. Then, we designed a face privacy recognition and protection model based on conditional generative adversarial networks. We verify our proposed method on two most commonly used face datasets in face research, namely CelebFaces Attributes and Labeled Faces in the Wild, and the results show that our proposed method achieve better performance compared with other face privacy protection methods. 

Online New Media Oriented Privacy Data Recognition Mechanism Based on Deep Learning

—The rapid adoption of facial recognition (FR) technology by both government and commercial entities in recent years has raised concerns about civil liberties and privacy. In response, a broad suite of so-called “anti-facial recognition” (AFR) tools has been developed to help users avoid unwanted facial recognition. The set of AFR tools proposed in the last few years is wide-ranging and rapidly evolving, necessitating a step back to consider the broader design space of AFR systems and long-term challenges. This paper aims to ﬁll that gap and provides the ﬁrst comprehensive analysis of the AFR research landscape. Using the operational stages of FR systems as a starting point, we create a systematic framework for analyzing the beneﬁts and tradeoffs of different AFR approaches. We then consider both technical and social challenges facing AFR tools and propose directions for future research in this ﬁeld.

SoK: Anti-Facial Recognition Technology

Face anti-spoofing aims to discriminate the spoofing face images (e.g., printed photos) from live ones. However, adversarial examples greatly challenge its credibility, where adding some perturbation noise can easily change the predictions. Previous works conducted adversarial attack methods to evaluate the face anti-spoofing performance without any fine-grained analysis that which model architecture or auxiliary feature is vulnerable to the adversary. To handle this problem, we propose a novel framework to expose the fine-grained adversarial vulnerability of the face anti-spoofing models, which consists of a multitask module and a semantic feature augmentation (SFA) module. The multitask module can obtain different semantic features for further evaluation, but only attacking these semantic features fails to reflect the discrimination-related vulnerability. We then design the SFA module to introduce the data distribution prior for more discrimination-related gradient directions for generating adversarial examples. Comprehensive experiments show that SFA module increases the attack success rate by nearly 40$\%$ on average. We conduct this fine-grained adversarial analysis on different annotations, geometric maps, and backbone networks (e.g., Resnet network). These fine-grained adversarial examples can be used for selecting robust backbone networks and auxiliary features. They also can be used for adversarial training, which makes it practical to further improve the accuracy and robustness of the face anti-spoofing models.

Exposing Fine-grained Adversarial Vulnerability of Face Anti-spoofing Models

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.

Yuehua Cheng

Papers

A Systematical Solution for Face De-identification

A Systematical Solution for Face De-identification