Data-agnostic Face Image Synthesis Detection using Bayesian CNNs

Roberto Leyva

doi:10.1016/j.patrec.2024.04.008

2024-07-01

DOI：10.1016/j.patrec.2024.04.008

原文链接

查看原文

摘要

En 中文

Face image synthesis detection is considerably gaining attention because of the potential negative impact on society that this type of synthetic data brings. In this paper, we propose a data-agnostic solution to detect the face image synthesis process. Specifically, our solution is based on an anomaly detection framework that requires only real data to learn the inference process. It is therefore data-agnostic in the sense that it requires no synthetic face images. The solution uses the posterior probability with respect to the reference data to determine if new samples are synthetic or not. Our evaluation results using different synthesizers show that our solution is very competitive against the state-of-the-art, which requires synthetic data for training.

Keyword:

Face synthesis

Deep fakes

Agnostic models

Anomaly detection

Computer security

AI总结

对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。

期刊

Pattern Recognition Letters

IF:

3.3

论文数:

8.0K

被引数:

1.6W

机构

University of Warwick

学者数:

2.2W

论文数: 2.2W

被引数: 85

引用论文

A deep-learning-based antifraud system for car-insurance claims 基于深度学习的汽车保险索赔反欺诈系统

EXPERT SYSTEMS WITH APPLICATIONS

IF7.5

2023-11-01

OAAI

Maiano, Luca; Montuschi, Antonio; Caserio, Marta; Ferri, Egon; Kieffer, Federico; Germano, Chiara; Baiocco, Lorenzo; Celsi, Lorenzo Ricciardi; Amerini, Irene; Anagnostopoulos, Aris

The use of facial motion and facial form during the processing of identity 在身份识别过程中使用面部运动和面部形式

Vision Research

IF0

2003-08-01

PREAI

Barbara Knappmeyer; Ian M Thornton; Heinrich H Bülthoff

Nano-sized ZnO powders prepared by co-precipitation method with various pH

AIP Conference Proceedings

IF0

2016-01-01

OAAI

S. Y. Purwaningsih; S. Pratapa; Triwikantoro; Darminto