Abstract
This paper proposes FakeBuster, a novel DeepFake detector for (a) detecting impostors during video conferencing, and (b) manipulated faces on social media. FakeBuster is a standalone deep learning- based solution, which enables a user to detect if another person's video is manipulated or spoofed during a video conference-based meeting. This tool is independent of video conferencing solutions and has been tested with Zoom and Skype applications. It employs a 3D convolutional neural network for predicting video fakeness. The network is trained on a combination of datasets such as Deeperforensics, DFDC, VoxCeleb, and deepfake videos created using locally captured images (specific to video conferencing scenarios). Diversity in the training data makes FakeBuster robust to multiple environments and facial manipulations, thereby making it generalizable and ecologically valid.
Original language | English |
---|---|
Title of host publication | 26th International Conference on Intelligent User Interfaces, IUI 2021 Companion |
Editors | Bart Knijnenburg, John O’Donovan, Paul Teale |
Place of Publication | New York NY USA |
Publisher | Association for Computing Machinery (ACM) |
Pages | 61-63 |
Number of pages | 3 |
ISBN (Electronic) | 9781450380188 |
DOIs | |
Publication status | Published - Apr 2021 |
Event | International Conference on Intelligent User Interfaces 2021: Where HCI Meets AI - Online, United States of America Duration: 14 Apr 2021 → 17 Apr 2021 Conference number: 26th https://dl.acm.org/doi/proceedings/10.1145/3397482 (Proceedings) |
Conference
Conference | International Conference on Intelligent User Interfaces 2021 |
---|---|
Abbreviated title | IUI 2021 |
Country/Territory | United States of America |
Period | 14/04/21 → 17/04/21 |
Internet address |
|
Keywords
- Deepfakes detection
- Neural networks
- Spoofing