UGAD: 利用频率指纹的通用生成式人工智能探测器

Inzamamul Alam, Muhammad Shahid Muneer, Simon S. Woo
{"title":"UGAD: 利用频率指纹的通用生成式人工智能探测器","authors":"Inzamamul Alam, Muhammad Shahid Muneer, Simon S. Woo","doi":"arxiv-2409.07913","DOIUrl":null,"url":null,"abstract":"In the wake of a fabricated explosion image at the Pentagon, an ability to\ndiscern real images from fake counterparts has never been more critical. Our\nstudy introduces a novel multi-modal approach to detect AI-generated images\namidst the proliferation of new generation methods such as Diffusion models.\nOur method, UGAD, encompasses three key detection steps: First, we transform\nthe RGB images into YCbCr channels and apply an Integral Radial Operation to\nemphasize salient radial features. Secondly, the Spatial Fourier Extraction\noperation is used for a spatial shift, utilizing a pre-trained deep learning\nnetwork for optimal feature extraction. Finally, the deep neural network\nclassification stage processes the data through dense layers using softmax for\nclassification. Our approach significantly enhances the accuracy of\ndifferentiating between real and AI-generated images, as evidenced by a 12.64%\nincrease in accuracy and 28.43% increase in AUC compared to existing\nstate-of-the-art methods.","PeriodicalId":501130,"journal":{"name":"arXiv - CS - Computer Vision and Pattern Recognition","volume":null,"pages":null},"PeriodicalIF":0.0000,"publicationDate":"2024-09-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"UGAD: Universal Generative AI Detector utilizing Frequency Fingerprints\",\"authors\":\"Inzamamul Alam, Muhammad Shahid Muneer, Simon S. Woo\",\"doi\":\"arxiv-2409.07913\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"In the wake of a fabricated explosion image at the Pentagon, an ability to\\ndiscern real images from fake counterparts has never been more critical. Our\\nstudy introduces a novel multi-modal approach to detect AI-generated images\\namidst the proliferation of new generation methods such as Diffusion models.\\nOur method, UGAD, encompasses three key detection steps: First, we transform\\nthe RGB images into YCbCr channels and apply an Integral Radial Operation to\\nemphasize salient radial features. Secondly, the Spatial Fourier Extraction\\noperation is used for a spatial shift, utilizing a pre-trained deep learning\\nnetwork for optimal feature extraction. Finally, the deep neural network\\nclassification stage processes the data through dense layers using softmax for\\nclassification. Our approach significantly enhances the accuracy of\\ndifferentiating between real and AI-generated images, as evidenced by a 12.64%\\nincrease in accuracy and 28.43% increase in AUC compared to existing\\nstate-of-the-art methods.\",\"PeriodicalId\":501130,\"journal\":{\"name\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":0.0000,\"publicationDate\":\"2024-09-12\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"arXiv - CS - Computer Vision and Pattern Recognition\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/arxiv-2409.07913\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"\",\"JCRName\":\"\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"arXiv - CS - Computer Vision and Pattern Recognition","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/arxiv-2409.07913","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"","JCRName":"","Score":null,"Total":0}
引用次数: 0

摘要

在五角大楼伪造爆炸图像事件发生后,辨别真假图像的能力变得前所未有的重要。在扩散模型等新一代方法层出不穷的情况下,我们的研究引入了一种新颖的多模态方法来检测人工智能生成的图像:首先,我们将 RGB 图像转换为 YCbCr 通道,并应用积分径向运算来强调突出的径向特征。其次,使用空间傅立叶提取操作进行空间转换,利用预先训练好的深度学习网络进行最佳特征提取。最后,深度神经网络分类阶段通过密集层处理数据,使用 softmax 进行分类。与现有的最先进方法相比,我们的方法大大提高了区分真实图像和人工智能生成图像的准确性,准确率提高了 12.64%,AUC 提高了 28.43%。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
UGAD: Universal Generative AI Detector utilizing Frequency Fingerprints
In the wake of a fabricated explosion image at the Pentagon, an ability to discern real images from fake counterparts has never been more critical. Our study introduces a novel multi-modal approach to detect AI-generated images amidst the proliferation of new generation methods such as Diffusion models. Our method, UGAD, encompasses three key detection steps: First, we transform the RGB images into YCbCr channels and apply an Integral Radial Operation to emphasize salient radial features. Secondly, the Spatial Fourier Extraction operation is used for a spatial shift, utilizing a pre-trained deep learning network for optimal feature extraction. Finally, the deep neural network classification stage processes the data through dense layers using softmax for classification. Our approach significantly enhances the accuracy of differentiating between real and AI-generated images, as evidenced by a 12.64% increase in accuracy and 28.43% increase in AUC compared to existing state-of-the-art methods.
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