Facial Privacy and Forensic in The Wild: Explainable End-to-End Networks for Multi-Face Anonymization and Multi-Face Forgery Detection

2021 Fiscal Year Final Research Report

• Project/Area Number: 20K23355
• Research Category: Grant-in-Aid for Research Activity Start-up
• Allocation Type: Multi-year Fund
• Review Section: 1002:Human informatics, applied informatics and related fields
• Research Institution: National Institute of Informatics
• Principal Investigator: Le Trung-Nghia 国立情報学研究所, 情報社会相関研究系, 特任研究員 (00884404)
• Project Period (FY): 2020-09-11 – 2022-03-31
• Keywords: deepfake generation / deepfake detection / deepfake segmentation

Outline of Final Research Achievements

We developed a forgery workflow to reduce the cost of synthesizing fake data. Our framework can generate an infinite number of fake individual identities using GAN models for non-target face-swapping without repeatedly training a deepfake generator. This framework has great potential in deepfake generation and face anonymization. We also created a new large-scale dataset with high-quality images for multi-face forgery detection and segmentation in-the-wild. It consists of 115K unrestricted images with 334K human faces. We also presented a benchmark suite to facilitate the evaluation and advancement of these tasks. Our work was published at ICCV 2021, a top-tier conference in computer vision.

Free Research Field

Applied Computer VIsion

Academic Significance and Societal Importance of the Research Achievements

We published a book chapter to introduce general knowledge about deepfake for beginners and/or students. We expect that our book chapter is helpful for beginners to understand deepfake and use these techniques correctly.