Mastering Deepfake Detection: A Cutting-edge Approach to Distinguish GAN and Diffusion-model Images

Author:

Guarnera Luca1ORCID,Giudice Oliver2ORCID,Battiato Sebastiano1ORCID

Affiliation:

1. Department of Mathematics and Computer Science, University of Catania, Catania, Italy

2. Banca d'Italia, Roma, Italy

Abstract

Detecting and recognizing deepfakes is a pressing issue in the digital age. In this study, we first collected a dataset of pristine images and fake ones properly generated by nine different Generative Adversarial Network (GAN) architectures and four Diffusion Models (DM). The dataset contained a total of 83,000 images, with equal distribution between the real and deepfake data. Then, to address different deepfake detection and recognition tasks, we proposed a hierarchical multi-level approach. At the first level, we classified real images from AI-generated ones. At the second level, we distinguished between images generated by GANs and DMs. At the third level (composed of two additional sub-levels), we recognized the specific GAN and DM architectures used to generate the synthetic data. Experimental results demonstrated that our approach achieved more than 97% classification accuracy, outperforming existing state-of-the-art methods. The models obtained in the different levels turn out to be robust to various attacks such as JPEG compression (with different quality factor values) and resize (and others), demonstrating that the framework can be used and applied in real-world contexts (such as the analysis of multimedia data shared in the various social platforms) for support even in forensic investigations to counter the illicit use of these powerful and modern generative models. We are able to identify the specific GAN and DM architecture used to generate the image, which is critical in tracking down the source of the deepfake. Our hierarchical multi-level approach to deepfake detection and recognition shows promising results in identifying deepfakes allowing focus on underlying task by improving (about 2% on the average) standard multiclass flat detection systems. The proposed method has the potential to enhance the performance of deepfake detection systems, aid in the fight against the spread of fake images, and safeguard the authenticity of digital media.

Publisher

Association for Computing Machinery (ACM)

Reference48 articles.

1. A siamese-based verification system for open-set architecture attribution of synthetic images;Abady Lydia;arXiv preprint arXiv:2307.09822,2023

2. Parents and children: Distinguishing multimodal deepfakes from natural images;Amoroso Roberto;arXiv preprint arXiv:2304.00500,2023

3. Sebastiano Battiato, Oliver Giudice, and Antonino Paratore. 2016. Multimedia forensics: Discovering the history of multimedia contents. In Proceedings of the 17th International Conference on Computer Systems and Technologies. 5–16.

4. Sebastiano Battiato, Massimo Mancuso, Angelo Bosco, and Mirko Guarnera. 2001. Psychovisual and statistical optimization of quantization tables for DCT compression engines. In Proceedings of the 11th International Conference on Image Analysis and Processing. IEEE, 602–606.

5. Wonwoong Cho, Sungha Choi, David Keetae Park, Inkyu Shin, and Jaegul Choo. 2019. Image-to-image translation via group-wise deep whitening-and-coloring transformation. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition. 10639–10647.

Cited by 3 articles. 订阅此论文施引文献 订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献

1. GenAI mirage: The impostor bias and the deepfake detection challenge in the era of artificial illusions;Forensic Science International: Digital Investigation;2024-09

2. Introduction to Special Issue on “Recent trends in Multimedia Forensics”;ACM Transactions on Multimedia Computing, Communications, and Applications;2024-08-02

3. Making Original 2D Visual Deepfakes With a Generative AI Tool;Advances in Multimedia and Interactive Technologies;2024-07-17

同舟云学术

1.学者识别学者识别

2.学术分析学术分析

3.人才评估人才评估

"同舟云学术"是以全球学者为主线,采集、加工和组织学术论文而形成的新型学术文献查询和分析系统,可以对全球学者进行文献检索和人才价值评估。用户可以通过关注某些学科领域的顶尖人物而持续追踪该领域的学科进展和研究前沿。经过近期的数据扩容,当前同舟云学术共收录了国内外主流学术期刊6万余种,收集的期刊论文及会议论文总量共计约1.5亿篇,并以每天添加12000余篇中外论文的速度递增。我们也可以为用户提供个性化、定制化的学者数据。欢迎来电咨询!咨询电话:010-8811{复制后删除}0370

www.globalauthorid.com

TOP

Copyright © 2019-2024 北京同舟云网络信息技术有限公司
京公网安备11010802033243号  京ICP备18003416号-3