Masked Conditional Diffusion Model for Enhancing Deepfake Detection

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Chen, Tiewen, Yang, Shanmin, Hu, Shu, Fang, Zhenghan, Fu, Ying, Wu, Xi, Wang, Xin
Format: Preprint
Published: 2024
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914662771064832
author Chen, Tiewen
Yang, Shanmin
Hu, Shu
Fang, Zhenghan
Fu, Ying
Wu, Xi
Wang, Xin
author_facet Chen, Tiewen
Yang, Shanmin
Hu, Shu
Fang, Zhenghan
Fu, Ying
Wu, Xi
Wang, Xin
contents Recent studies on deepfake detection have achieved promising results when training and testing faces are from the same dataset. However, their results severely degrade when confronted with forged samples that the model has not yet seen during training. In this paper, deepfake data to help detect deepfakes. this paper present we put a new insight into diffusion model-based data augmentation, and propose a Masked Conditional Diffusion Model (MCDM) for enhancing deepfake detection. It generates a variety of forged faces from a masked pristine one, encouraging the deepfake detection model to learn generic and robust representations without overfitting to special artifacts. Extensive experiments demonstrate that forgery images generated with our method are of high quality and helpful to improve the performance of deepfake detection models.
format Preprint
id arxiv_https___arxiv_org_abs_2402_00541
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle Masked Conditional Diffusion Model for Enhancing Deepfake Detection
Chen, Tiewen
Yang, Shanmin
Hu, Shu
Fang, Zhenghan
Fu, Ying
Wu, Xi
Wang, Xin
Computer Vision and Pattern Recognition
Recent studies on deepfake detection have achieved promising results when training and testing faces are from the same dataset. However, their results severely degrade when confronted with forged samples that the model has not yet seen during training. In this paper, deepfake data to help detect deepfakes. this paper present we put a new insight into diffusion model-based data augmentation, and propose a Masked Conditional Diffusion Model (MCDM) for enhancing deepfake detection. It generates a variety of forged faces from a masked pristine one, encouraging the deepfake detection model to learn generic and robust representations without overfitting to special artifacts. Extensive experiments demonstrate that forgery images generated with our method are of high quality and helpful to improve the performance of deepfake detection models.
title Masked Conditional Diffusion Model for Enhancing Deepfake Detection
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2402.00541