改进跨概念设置下的综合生成图像检测

P. Dogoulis, Giorgos Kordopatis-Zilos, I. Kompatsiaris, S. Papadopoulos
{"title":"改进跨概念设置下的综合生成图像检测","authors":"P. Dogoulis, Giorgos Kordopatis-Zilos, I. Kompatsiaris, S. Papadopoulos","doi":"10.1145/3592572.3592846","DOIUrl":null,"url":null,"abstract":"New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and speed. In this paper, we focus on the challenge of generalizing across different concept classes, e.g., when training a detector on human faces and testing on synthetic animal images – highlighting the ineffectiveness of existing approaches that randomly sample generated images to train their models. By contrast, we propose an approach based on the premise that the robustness of the detector can be enhanced by training it on realistic synthetic images that are selected based on their quality scores according to a probabilistic quality estimation model. We demonstrate the effectiveness of the proposed approach by conducting experiments with generated images from two seminal architectures, StyleGAN2 and Latent Diffusion, and using three different concepts for each, so as to measure the cross-concept generalization ability. Our results show that our quality-based sampling method leads to higher detection performance for nearly all concepts, improving the overall effectiveness of the synthetic image detectors.","PeriodicalId":239252,"journal":{"name":"Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation","volume":"10 1","pages":"0"},"PeriodicalIF":0.0000,"publicationDate":"2023-04-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"6","resultStr":"{\"title\":\"Improving Synthetically Generated Image Detection in Cross-Concept Settings\",\"authors\":\"P. Dogoulis, Giorgos Kordopatis-Zilos, I. Kompatsiaris, S. Papadopoulos\",\"doi\":\"10.1145/3592572.3592846\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and speed. In this paper, we focus on the challenge of generalizing across different concept classes, e.g., when training a detector on human faces and testing on synthetic animal images – highlighting the ineffectiveness of existing approaches that randomly sample generated images to train their models. By contrast, we propose an approach based on the premise that the robustness of the detector can be enhanced by training it on realistic synthetic images that are selected based on their quality scores according to a probabilistic quality estimation model. We demonstrate the effectiveness of the proposed approach by conducting experiments with generated images from two seminal architectures, StyleGAN2 and Latent Diffusion, and using three different concepts for each, so as to measure the cross-concept generalization ability. Our results show that our quality-based sampling method leads to higher detection performance for nearly all concepts, improving the overall effectiveness of the synthetic image detectors.\",\"PeriodicalId\":239252,\"journal\":{\"name\":\"Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation\",\"volume\":\"10 1\",\"pages\":\"0\"},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2023-04-24\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"6\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.1145/3592572.3592846\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Proceedings of the 2nd ACM International Workshop on Multimedia AI against Disinformation","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.1145/3592572.3592846","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 6

摘要

合成图像检测的新进展对于打击虚假信息至关重要,因为生成式人工智能模型的能力不断发展,并可能以前所未有的规模和速度产生超逼真的合成图像。在本文中,我们关注的是跨不同概念类进行泛化的挑战,例如,在人脸上训练检测器和在合成动物图像上测试时——强调了随机采样生成图像来训练模型的现有方法的有效性。相比之下,我们提出了一种基于前提的方法,即检测器的鲁棒性可以通过在根据概率质量估计模型根据质量分数选择的真实合成图像上进行训练来增强。我们通过对StyleGAN2和Latent Diffusion这两个重要架构生成的图像进行实验,并对每个架构使用三个不同的概念,来验证所提出方法的有效性,从而衡量跨概念泛化能力。我们的研究结果表明,基于质量的采样方法对几乎所有概念都有更高的检测性能,提高了合成图像检测器的整体效率。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
Improving Synthetically Generated Image Detection in Cross-Concept Settings
New advancements for the detection of synthetic images are critical for fighting disinformation, as the capabilities of generative AI models continuously evolve and can lead to hyper-realistic synthetic imagery at unprecedented scale and speed. In this paper, we focus on the challenge of generalizing across different concept classes, e.g., when training a detector on human faces and testing on synthetic animal images – highlighting the ineffectiveness of existing approaches that randomly sample generated images to train their models. By contrast, we propose an approach based on the premise that the robustness of the detector can be enhanced by training it on realistic synthetic images that are selected based on their quality scores according to a probabilistic quality estimation model. We demonstrate the effectiveness of the proposed approach by conducting experiments with generated images from two seminal architectures, StyleGAN2 and Latent Diffusion, and using three different concepts for each, so as to measure the cross-concept generalization ability. Our results show that our quality-based sampling method leads to higher detection performance for nearly all concepts, improving the overall effectiveness of the synthetic image detectors.
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