Search Results for author: Pu Sun

Found 5 papers, 2 papers with code

FakeTracer: Proactively Defending Against Face-swap DeepFakes via Implanting Traces in Training

no code implementations27 Jul 2023 Pu Sun, Honggang Qi, Yuezun Li, Siwei Lyu

Face-swap DeepFake is an emerging AI-based face forgery technique that can replace the original face in a video with a generated face of the target identity while retaining consistent facial attributes such as expression and orientation.

Face Generation Face Swapping

DeepFake-o-meter: An Open Platform for DeepFake Detection

no code implementations2 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.

DeepFake Detection Face Swapping

Landmark Breaker: Obstructing DeepFake By Disturbing Landmark Extraction

no code implementations1 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.

Face Swapping

LandmarkGAN: Synthesizing Faces from Landmarks

1 code implementation31 Oct 2020 Pu Sun, Yuezun Li, Honggang Qi, Siwei Lyu

Face synthesis is an important problem in computer vision with many applications.

Face Generation

Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics

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.

DeepFake Detection Face Swapping

Cannot find the paper you are looking for? You can Submit a new open access paper.