An automatic deepfake technology integration pipeline for benchmarking deepfake detection methods

Project Member(s): Yu, X.

Funding or Partner Organisation: Defence Science and Technology Group of the Department of Defence (DAIRNet - AI for Decision Making)
Defence Science and Technology Group of the Department of Defence (DAIRNet - AI for Decision Making)

Start year: 2022

Summary: This project will present a Deepfake integration platform that can continuously integrate data generated by newly invented Deepfake techniques into a benchmark while balancing the ratio between real and Deepfake data. Specifically, this platform will provide an interface that incorporates data generated by various Deepfake techniques into a benchmark. As the number of Deepfake data increases, fabricated data might dominate the benchmark and lead to an imbalanced dataset. Hence, the platform will also dynamically maintain the balance between real and fake data in the benchmark by further collecting authentic untouched content.

FOR Codes: Computer vision, Image processing, Emerging defence technologies

Acknowledgement of Country

UTS acknowledges the Gadigal people of the Eora Nation, the Boorooberongal people of the Dharug Nation, the Bidiagal people and the Gamaygal people, upon whose ancestral lands our university stands. We would also like to pay respect to the Elders both past and present, acknowledging them as the traditional custodians of knowledge for these lands.