Facial Privacy and Forensic in The Wild: Explainable End-to-End Networks for Multi-Face Anonymization and Multi-Face Forgery Detection
| 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
|
| Project Status |
Completed (Fiscal Year 2021)
|
| Budget Amount *help |
¥2,860,000 (Direct Cost: ¥2,200,000、Indirect Cost: ¥660,000)
Fiscal Year 2021: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
Fiscal Year 2020: ¥1,430,000 (Direct Cost: ¥1,100,000、Indirect Cost: ¥330,000)
|
|---|
| Keywords | deepfake generation / deepfake detection / deepfake segmentation / Face forgery detection / Deepfake generation / Adversarial attack / Forgery detection / Face anonymization / Explainable AI / Multi-task learning / Object detection |
|---|
| Outline of Research at the Start |
This research aims to explore multi-face anonymization and multi-face forgery detection in the wild by utilizing their complementary. We also investigate explainable AI to improve the reliability and the robustness against adversarial attacks.
|
| 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.
|
| 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.
|
Report
(3 results)
Research Products
(10 results)
-
-
-
[Journal Article] Interactive Video Object Mask Annotation2021
Author(s)
Trung-Nghia Le, Tam V. Nguyen, Quoc-Cuong Tran, Lam Nguyen, Trung-Hieu Hoang, Minh-Quan Le, Minh-Triet Tran
-
Journal Title
AAAI Conference on Artificial Intelligence
Volume: 35
Pages: 16067-16070
Related Report
Peer Reviewed / Int'l Joint Research
-
-
-
-
-
-
-
