no code implementations • 27 Jul 2023 • Pu Sun, Honggang Qi, Yuezun Li, Siwei Lyu
In light of these two traces, our method can effectively expose DeepFakes by identifying them.
no code implementations • 2 Mar 2021 • Yuezun Li, Cong Zhang, Pu Sun, Honggang Qi, Siwei Lyu
In recent years, the advent of deep learning-based techniques and the significant reduction in the cost of computation resulted in the feasibility of creating realistic videos of human faces, commonly known as DeepFakes.
no code implementations • 1 Feb 2021 • Pu Sun, Yuezun Li, Honggang Qi, Siwei Lyu
In this paper, we describe Landmark Breaker, the first dedicated method to disrupt facial landmark extraction, and apply it to the obstruction of the generation of DeepFake videos. Our motivation is that disrupting the facial landmark extraction can affect the alignment of input face so as to degrade the DeepFake quality.
1 code implementation • 31 Oct 2020 • Pu Sun, Yuezun Li, Honggang Qi, Siwei Lyu
Face synthesis is an important problem in computer vision with many applications.
7 code implementations • CVPR 2020 • Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, Siwei Lyu
AI-synthesized face-swapping videos, commonly known as DeepFakes, is an emerging problem threatening the trustworthiness of online information.