English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

The privacy and security of face data on social media are facingunprecedented challenges as it is vulnerable to unauthorized access andidentification. A common practice for solving this problem is to modify theoriginal data so that it could be protected from being recognized by maliciousface recognition (FR) systems. However, such ``adversarial examples'' obtainedby existing methods usually suffer from low transferability and poor imagequality, which severely limits the application of these methods in real-worldscenarios. In this paper, we propose a 3D-Aware Adversarial Makeup GenerationGAN (3DAM-GAN). which aims to improve the quality and transferability ofsynthetic makeup for identity information concealing. Specifically, a UV-basedgenerator consisting of a novel Makeup Adjustment Module (MAM) and MakeupTransfer Module (MTM) is designed to render realistic and robust makeup withthe aid of symmetric characteristics of human faces. Moreover, a makeup attackmechanism with an ensemble training strategy is proposed to boost thetransferability of black-box models. Extensive experiment results on severalbenchmark datasets demonstrate that 3DAM-GAN could effectively protect facesagainst various FR models, including both publicly available state-of-the-artmodels and commercial face verification APIs, such as Face++, Baidu and Aliyun.

3D-Aware Adversarial Makeup Generation for Facial Privacy Protection