基于眼睛的Siamese神经网络检测gan生成的人脸图像

IF 1.3 Q3 ENGINEERING, ELECTRICAL & ELECTRONIC
Jun Wang , B. Tondi, M. Barni
{"title":"基于眼睛的Siamese神经网络检测gan生成的人脸图像","authors":"Jun Wang , B. Tondi, M. Barni","doi":"10.3389/frsip.2022.918725","DOIUrl":null,"url":null,"abstract":"Generative Adversarial Network (GAN) models are nowadays able to generate synthetic images which are visually indistinguishable from the real ones, thus raising serious concerns about the spread of fake news and the need to develop tools to distinguish fake and real images in order to preserve the trustworthiness of digital images. The most powerful current detection methods are based on Deep Learning (DL) technology. While these methods get excellent performance when tested under conditions similar to those considered for training, they often suffer from a lack of robustness and generalization ability, as they fail to detect fake images that are generated by “unseen” GAN models. A possibility to overcome this problem is to develop tools that rely on the semantic attributes of the image. In this paper, we propose a semantic-based method for distinguishing GAN-generated from real faces, that relies on the analysis of inter-eye symmetries and inconsistencies. The method resorts to the superior capabilities of similarity learning of extracting representative and robust features. More specifically, a Siamese Neural Network (SNN) is utilized to extract high-level features characterizing the inter-eye similarity, that can be used to discriminate between real and synthetic pairs of eyes. We carried out extensive experiments to assess the performance of the proposed method in both matched and mismatched conditions pertaining to the GAN type used to generate the synthetic images and the robustness of the method in presence of post-processing. The results we got are comparable, and in some cases superior, to those achieved by the best performing state-of-the-art method leveraging on the analysis of the entire face image.","PeriodicalId":93557,"journal":{"name":"Frontiers in signal processing","volume":"15 1","pages":""},"PeriodicalIF":1.3000,"publicationDate":"2022-07-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"4","resultStr":"{\"title\":\"An Eyes-Based Siamese Neural Network for the Detection of GAN-Generated Face Images\",\"authors\":\"Jun Wang , B. Tondi, M. Barni\",\"doi\":\"10.3389/frsip.2022.918725\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Generative Adversarial Network (GAN) models are nowadays able to generate synthetic images which are visually indistinguishable from the real ones, thus raising serious concerns about the spread of fake news and the need to develop tools to distinguish fake and real images in order to preserve the trustworthiness of digital images. The most powerful current detection methods are based on Deep Learning (DL) technology. While these methods get excellent performance when tested under conditions similar to those considered for training, they often suffer from a lack of robustness and generalization ability, as they fail to detect fake images that are generated by “unseen” GAN models. A possibility to overcome this problem is to develop tools that rely on the semantic attributes of the image. In this paper, we propose a semantic-based method for distinguishing GAN-generated from real faces, that relies on the analysis of inter-eye symmetries and inconsistencies. The method resorts to the superior capabilities of similarity learning of extracting representative and robust features. More specifically, a Siamese Neural Network (SNN) is utilized to extract high-level features characterizing the inter-eye similarity, that can be used to discriminate between real and synthetic pairs of eyes. We carried out extensive experiments to assess the performance of the proposed method in both matched and mismatched conditions pertaining to the GAN type used to generate the synthetic images and the robustness of the method in presence of post-processing. The results we got are comparable, and in some cases superior, to those achieved by the best performing state-of-the-art method leveraging on the analysis of the entire face image.\",\"PeriodicalId\":93557,\"journal\":{\"name\":\"Frontiers in signal processing\",\"volume\":\"15 1\",\"pages\":\"\"},\"PeriodicalIF\":1.3000,\"publicationDate\":\"2022-07-08\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"4\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Frontiers in signal processing\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.3389/frsip.2022.918725\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q3\",\"JCRName\":\"ENGINEERING, ELECTRICAL & ELECTRONIC\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Frontiers in signal processing","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.3389/frsip.2022.918725","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"ENGINEERING, ELECTRICAL & ELECTRONIC","Score":null,"Total":0}
引用次数: 4

摘要

如今,生成对抗网络(GAN)模型能够生成在视觉上与真实图像无法区分的合成图像,从而引发了对假新闻传播的严重担忧,以及开发区分假图像和真实图像的工具的必要性,以保持数字图像的可信度。目前最强大的检测方法是基于深度学习(DL)技术。虽然这些方法在类似于训练的条件下测试时获得了出色的性能,但它们往往缺乏鲁棒性和泛化能力,因为它们无法检测到由“看不见的”GAN模型生成的假图像。克服这个问题的一种可能性是开发依赖于图像语义属性的工具。在本文中,我们提出了一种基于语义的方法来区分gan生成的人脸和真实人脸,该方法依赖于对眼间对称性和不一致性的分析。该方法利用相似性学习提取代表性和鲁棒性特征的优越能力。更具体地说,使用连体神经网络(SNN)提取表征眼间相似性的高级特征,可用于区分真实和合成的眼睛。我们进行了大量的实验,以评估所提出的方法在与用于生成合成图像的GAN类型相关的匹配和不匹配条件下的性能,以及该方法在后处理中存在的鲁棒性。我们得到的结果是相当的,在某些情况下,优于那些表现最好的最先进的方法,利用整个面部图像的分析。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
An Eyes-Based Siamese Neural Network for the Detection of GAN-Generated Face Images
Generative Adversarial Network (GAN) models are nowadays able to generate synthetic images which are visually indistinguishable from the real ones, thus raising serious concerns about the spread of fake news and the need to develop tools to distinguish fake and real images in order to preserve the trustworthiness of digital images. The most powerful current detection methods are based on Deep Learning (DL) technology. While these methods get excellent performance when tested under conditions similar to those considered for training, they often suffer from a lack of robustness and generalization ability, as they fail to detect fake images that are generated by “unseen” GAN models. A possibility to overcome this problem is to develop tools that rely on the semantic attributes of the image. In this paper, we propose a semantic-based method for distinguishing GAN-generated from real faces, that relies on the analysis of inter-eye symmetries and inconsistencies. The method resorts to the superior capabilities of similarity learning of extracting representative and robust features. More specifically, a Siamese Neural Network (SNN) is utilized to extract high-level features characterizing the inter-eye similarity, that can be used to discriminate between real and synthetic pairs of eyes. We carried out extensive experiments to assess the performance of the proposed method in both matched and mismatched conditions pertaining to the GAN type used to generate the synthetic images and the robustness of the method in presence of post-processing. The results we got are comparable, and in some cases superior, to those achieved by the best performing state-of-the-art method leveraging on the analysis of the entire face image.
求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
自引率
0.00%
发文量
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
copy
已复制链接
快去分享给好友吧!
我知道了
右上角分享
点击右上角分享
0
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信