检索结果-内蒙古大学图书馆

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Liu, Huan Tang, Zichang Tan, Chuangchuang Wei, Yunchao Wang, Jingdong Zhao, Yao Beijing Jiaotong Univ Inst Informat Sci Beijing Peoples R China Baidu VIS Beijing Peoples R China Beijing Key Lab Adv Informat Sci & Network Techno Beijing Peoples R China

ISBN: (纸本)9798350353006

In this paper, we study the problem of generalizable synthetic image detection, aiming to detect forgery images from diverse generative methods, e.g., GANs and diffusion models. Cutting-edge solutions start to explore the benefits of pre-trained models, and mainly follow the fixed paradigm of solely training an attached classifier, e.g., combining frozen CLIP-ViT with a learnable linear layer in UniFD [43]. However, our analysis shows that such a fixed paradigm is prone to yield detectors with insufficient learning regarding forgery representations. We attribute the key challenge to the lack of forgery adaptation, and present a novel forgery-aware adaptive transformer approach, namely FatFormer. Based on the pre-trained vision-language spaces of CLIP, FatFormer introduces two core designs for the adaption to build generalized forgery representations. First, motivated by the fact that both image and frequency analysis are essential for synthetic image detection, we develop a forgery-aware adapter to adapt image features to discern and integrate local forgery traces within image and frequency do-mains. Second, we find that considering the contrastive objectives between adapted image features and text prompt embeddings, a previously overlooked aspect, results in a nontrivial generalization improvement. Accordingly, we introduce language-guided alignment to supervise the forgery adaptation with image and text prompts in FatFormer. Experiments show that, by coupling these two designs, our approach tuned on 4-class ProGAN data attains a remarkable detection performance, achieving an average of 98% accuracy to unseen GANs, and surprisingly generalizes to unseen diffusion models with 95% accuracy.

关键词： Forgery Adaptation synthetic image detection

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Generalization of synthetic image detection Models through the Exploration of Features in Deep detection Models 13

Enhancing the Generalization of Synthetic Image Detection Mo...

引用

13th Iranian/3rd International Machine Vision and image Processing Conference (MVIP)

作者： Javaheri, Alireza Hajabdollah Motamednia, Hossein Mahmoudi-Azanveh, Ahmad Shahid Beheshti Univ Cyberspace Res Inst Tehran Iran Inst Res Fundamental Sci Sch Comp Sci High Performance Comp Lab Tehran Iran

ISBN: (纸本)9798350350494;9798350350500

One of the major challenges of AI is the misuse of images generated by generative models. Advances in this field have reached a point where distinguishing between real and fake images can be impossible for humans and challenging even for machines. Although significant work has been done on detecting fake images, there is an ongoing competition between content generation and detection methods. However, a significant challenge for detection methods is their limitation to content generated by specific models. This study aims to enhance the generalization of fake image detection methods. Experimental results indicate that modifications made to the base model have contributed to improving its generalizability.

关键词： synthetic image detection image Forensics GANs Diffusion Models CNN

来源：评论

学校读者我要写书评

暂无评论

Less is more: A minimalist approach to robust GAN-generated face detection

引用

PATTERN RECOGNITION LETTERS 2024年 179卷 185-191页

作者： Ghosh, Tanusree Naskar, Ruchira Indian Inst Engn Sci & Technol Dept Informat Technol Sibpur 711103 India

Hyper-realistic images that are not differentiable from authentic images to regular viewers have become extremely easy to generate and highly accessible. Furthermore, the increasing pervasiveness of social media networks in our daily lives has facilitated the easy dissemination of fake news accompanied by such synthetic images. Hyper-realistic artificial face images are often illicitly used as profile pictures on social media sites, further using such profiles to spread fabricated information, resulting in social perils. Most available synthetic image detectors are challenging to implement in practical scenarios due to their high complexity and performance degradation for images from Online Social Networks (OSNs). In this work, we develop a deep learning-based lightweight synthetic image detector called Relative Chrominance Distance Network (RCD-Net). In this paper, we introduce the RCD image feature set for the first time, which gives a pair-wise chrominance component-based distance measure. To show its effectiveness, we explore multiple luminancechrominance spaces. Compared to the state -of -the -art (SOTA), our model hugely reduces the network parameter requirements, making it incredibly lightweight. We also study the robustness of the proposed solution against common post-processing operations in the context of online social media networks. Experimental results prove that the proposed solution achieves SOTA performance at a much lower complexity than available solutions.

关键词： Fake image detection Deepfake detection GAN forensics Digital image forensics synthetic image detection GAN-face detection

来源：评论

学校读者我要写书评

暂无评论

Detecting images generated by diffusers

引用

PEERJ COMPUTER SCIENCE 2024年 10卷 e2127页

作者： Coccomini, Davide Alessandro Esuli, Andrea Falchi, Fabrizio Gennaro, Claudio Amato, Giuseppe Italian Natl Res Council Inst Informat Sci & Technol Alessandro Faedo Pisa Tuscany Italy Univ Pisa Informat Engn Pisa Tuscany Italy

In recent years, the field of artificial intelligence has witnessed a remarkable surge in the generation of synthetic images, driven by advancements in deep learning techniques. These synthetic images, often created through complex algorithms, closely mimic real photographs, blurring the lines between reality and artificiality. This proliferation of synthetic visuals presents a pressing challenge: how to accurately and reliably distinguish between genuine and generated images. This article, in particular, explores the task of detecting images generated by text-to-image diffusion models, highlighting the challenges and peculiarities of this field. To evaluate this, we consider images generated from captions in the MSCOCO and Wikimedia datasets using two state-of-the-art models: Stable Diffusion and GLIDE. Our experiments show that it is possible to detect the generated images using simple multi-layer perceptrons (MLPs), starting from features extracted by CLIP or RoBERTa, or using traditional convolutional neural networks (CNNs). These latter models achieve remarkable performances in particular when pretrained on large datasets. We also observe that models trained on images generated by Stable Diffusion can occasionally detect images generated by GLIDE, but only on the MSCOCO dataset. However, the reverse is not true. Lastly, we find that incorporating the associated textual information with the images in some cases can lead to a better generalization capability, especially if textual features are closely related to visual ones. We also discovered that the type of subject depicted in the image can significantly impact performance. This work provides insights into the feasibility of detecting generated images and has implications for security and privacy concerns in real-world applications. The code to reproduce our results is available at: https://***/ davide-coccomini/Detecting-images-Generated-by-Diffusers.

关键词： Deepfake detection Computer vision Deep learning synthetic image detection CLIP Multimodal machine learning Convolutional neural networks Transformers

来源：评论

学校读者我要写书评

暂无评论

Synthbuster: Towards detection of Diffusion Model Generated images

IEEE OPEN JOURNAL OF SIGNAL PROCESSING

引用

IEEE OPEN JOURNAL OF SIGNAL PROCESSING 2024年 5卷 1-9页

作者： Bammey, Quentin Univ Paris Saclay ENS Paris Saclay CNRS Ctr Borelli F-91190 Gif Sur Yvette France

synthetically-generated images are getting increasingly popular. Diffusion models have advanced to the stage where even non-experts can generate photo-realistic images from a simple text prompt. They expand creative horizons but also open a Pandora's box of potential disinformation risks. In this context, the present corpus of synthetic image detection techniques, primarily focusing on older generative models like Generative Adversarial Networks, finds itself ill-equipped to deal with this emerging trend. Recognizing this challenge, we introduce a method specifically designed to detect synthetic images produced by diffusion models. Our approach capitalizes on the inherent frequency artefacts left behind during the diffusion process. Spectral analysis is used to highlight the artefacts in the Fourier transform of a residual image, which are used to distinguish real from fake images. The proposed method can detect diffusion-model-generated images even under mild jpeg compression, and generalizes relatively well to unknown models. By pioneering this novel approach, we aim to fortify forensic methodologies and ignite further research into the detection of AI-generated images.

关键词： Transform coding image coding Computational modeling image synthesis Databases Computer architecture Training Diffusion models image forensics media forensics multimedia forensics spectral analysis synthetic image detection

来源：评论

学校读者我要写书评

暂无评论

Reliable Out-of-Distribution Recognition of synthetic images

引用

JOURNAL OF IMAGING 2024年第5期10卷 110-110页

作者： Maier, Anatol Riess, Christian Univ Erlangen Nurnberg FAU Dept Comp Sci IT Secur Infrastruct Lab D-91058 Erlangen Germany

Generative adversarial networks (GANs) and diffusion models (DMs) have revolutionized the creation of synthetically generated but realistic-looking images. Distinguishing such generated images from real camera captures is one of the key tasks in current multimedia forensics research. One particular challenge is the generalization to unseen generators or post-processing. This can be viewed as an issue of handling out-of-distribution inputs. Forensic detectors can be hardened by the extensive augmentation of the training data or specifically tailored networks. Nevertheless, such precautions only manage but do not remove the risk of prediction failures on inputs that look reasonable to an analyst but in fact are out of the training distribution of the network. With this work, we aim to close this gap with a Bayesian Neural Network (BNN) that provides an additional uncertainty measure to warn an analyst of difficult decisions. More specifically, the BNN learns the task at hand and also detects potential confusion between post-processing and image generator artifacts. Our experiments show that the BNN achieves on-par performance with the state-of-the-art detectors while producing more reliable predictions on out-of-distribution examples.

关键词： synthetic image detection out-of-distribution examples Bayesian Neural Networks variational inference

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Exploration on Detecting Fake images Generated by Stable Diffusion 7th

A Comprehensive Exploration on Detecting Fake Images Generat...

引用

7th Chinese Conference on Pattern Recognition and Computer Vision

作者： Chen, Jingyi Wang, Xiaolong He, Zhijian Peng, Xiaojiang Shenzhen Technol Univ Shenzhen Peoples R China

ISBN: (纸本)9789819784868;9789819784875

Diffusion models, particularly Stable Diffusion Models (SDMs), have recently emerged as a focal point within the generative artificial intelligence sector, acclaimed for their superior visual fidelity and versatility. Despite their rising prominence, the challenge of detecting SDM-generated images has been somewhat overlooked, sparking concerns over their potential misuse for nefarious purposes. This paper aims to delve into the complexities of differentiating authentic images from those generated by SDMs, offering three significant contributions to the field. Firstly, we introduce a varied synthetic image dataset named SDM-Fakes, which consists of six subsets utilizing txt2img, img2img, and inpainting techniques. Secondly, we develop both CNN-based and Transformer-based detection models to identify artificial images, assessing a range of cutting-edge models. Thirdly, we pioneer the evaluation of these detection models' generalization capabilities across different schemes. We also explored the impact of unknown perturbations on those detectors. Through comprehensive testing, we demonstrate that while current models are adept at recognizing SDM-generated images, there is a significant need to enhance their ability to generalize cross-scheme tasks, as well as robustness on unknown perturbations.

关键词： Diffusion models image generation synthetic image detection

来源：评论

学校读者我要写书评

暂无评论

Did You Note My Palette? Unveiling synthetic images Through Color Statistics 24

Did You Note My Palette? Unveiling Synthetic Images Through ...

引用

12th ACM Workshop on Information Hiding and Multimedia Security (IH and MMSec)

作者： Uhlenbrock, Lea Cozzolino, Davide Moussa, Denise Verdoliva, Luisa Riess, Christian Friedrich Alexander Univ Erlangen Nurnberg Erlangen Germany Univ Napoli Federico II Naples Italy

ISBN: (纸本)9798400706370

High-quality artificially generated images are widely available now and increasingly realistic, posing challenges for image forensics in distinguishing them from real ones. Unfortunately, building a single detector that generalizes well to unseen generators is very difficult, creating the need for diverse cues. In this paper, we show that natural and synthetic images differ in their color statistics, possibly due to the widely used perceptual loss, which is more sensitive to brightness than to chroma differences. Consequently, color statistics offer valuable cues for forensic analysis and the development of robust detectors. Our experiments using simple hand-crafted color functions with a random forest achieve 91% accuracy averaged over all tested Diffusion Models, even with limited training samples.

关键词： image Forensics Color Spaces synthetic image detection Diffusion Models

来源：评论

学校读者我要写书评

暂无评论

Beyond Deepfake images: Detecting AI-Generated Videos

Beyond Deepfake Images: Detecting AI-Generated Videos

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Vandati, Danial Samadi Nguyen, Tai D. Azizpour, Aref Stamm, Matthew C. Drexel Univ Philadelphia PA 19104 USA

ISBN: (纸本)9798350365474

Recent advances in generative AI have led to the development of techniques to generate visually realistic synthetic video. While a number of techniques have been developed to detect AI-generated synthetic images, in this paper we show that synthetic image detectors are unable to detect synthetic videos. We demonstrate that this is because synthetic video generators introduce substantially different traces than those left by image generators. Despite this, we show that synthetic video traces can be learned, and used to perform reliable synthetic video detection or generator source attribution even after H.264 re-compression. Furthermore, we demonstrate that while detecting videos from new generators through zero-shot transferability is challenging, accurate detection of videos from a new generator can be achieved through few-shot learning.

关键词： Deep Learning Deep Neural Networks Deepfake Generative AI image forensics Media Forensics synthetic image detection synthetic images synthetic video detection synthetic Videos video forensics

来源：评论

学校读者我要写书评

暂无评论

E3: Ensemble of Expert Embedders for Adapting synthetic image Detectors to New Generators Using Limited Data

E3: Ensemble of Expert Embedders for Adapting Synthetic Imag...

引用

IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Azizpour, Aref Nguyen, Tai D. Shrestha, Manil Xu, Kaidi Kim, Edward Stamm, Matthew C. Drexel Univ Philadelphia PA 19104 USA

ISBN: (纸本)9798350365474

As generative AI progresses rapidly, new synthetic image generators continue to emerge at a swift pace. Traditional detection methods face two main challenges in adapting to these generators: the forensic traces of synthetic images from new techniques can vastly differ from those learned during training, and access to data for these new generators is often limited. To address these issues, we introduce the Ensemble of Expert Embedders (E3), a novel continual learning framework for updating synthetic image detectors. E3 enables the accurate detection of images from newly emerged generators using minimal training data. Our approach does this by first employing transfer learning to develop a suite of expert embedders, each specializing in the forensic traces of a specific generator. Then, all embeddings are jointly analyzed by an Expert Knowledge Fusion Network to produce accurate and reliable detection decisions. Our experiments demonstrate that E3 outperforms existing continual learning methods, including those developed specifically for synthetic image detection.

关键词： Contniual Learning Multimedia Forensics synthetic image detection synthetic images Transformers

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：