{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,15]],"date-time":"2026-07-15T11:33:18Z","timestamp":1784115198175,"version":"3.55.0"},"reference-count":46,"publisher":"Frontiers Media SA","license":[{"start":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T00:00:00Z","timestamp":1761091200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["frontiersin.org"],"crossmark-restriction":true},"short-container-title":["Front. Artif. Intell."],"abstract":"<jats:p>With the rapid advancement of AI-generated content, detecting synthetic images has become a critical task in digital forensics and media integrity. In this paper, we propose a novel multi-modal fusion network that leverages complementary texture and content information to improve the detection of AI-generated images. Our approach integrates three input branches: the original RGB image, a local binary pattern (LBP) map to capture micro-texture irregularities, and a gray-level co-occurrence matrix (GLCM) representation to encode statistical texture dependencies. These three streams are processed in parallel through a shared-weight convolutional backbone and subsequently fused at the feature level to enhance discrimination capability. Extensive experiments conducted on benchmark datasets demonstrate that our method outperforms existing single-modality baselines and achieves strong generalization across multiple types of generative models. The proposed fusion framework offers an interpretable and efficient solution for robust and reliable detection of AI-synthesized imagery.<\/jats:p>","DOI":"10.3389\/frai.2025.1663292","type":"journal-article","created":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:32:29Z","timestamp":1761111149000},"update-policy":"https:\/\/doi.org\/10.3389\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Multi-modal texture fusion network for detecting AI-generated images"],"prefix":"10.3389","volume":"8","author":[{"given":"Haozheng","family":"Yu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Bing","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1965","published-online":{"date-parts":[[2025,10,22]]},"reference":[{"key":"B1","doi-asserted-by":"crossref","first-page":"4332","DOI":"10.1145\/3627673.3680085","article-title":"\u201cUGAD: universal generative AI detector utilizing frequency fingerprints,\u201d","volume-title":"Proceedings of the 33rd ACM International Conference on Information and Knowledge Management","author":"Alam","year":"2024"},{"key":"B2","doi-asserted-by":"publisher","first-page":"103097","DOI":"10.1016\/j.jvcir.2021.103097","article-title":"Hybrid prediction-based pixel-value-ordering method for reversible data hiding","volume":"77","author":"Chang","year":"2021","journal-title":"J. Vis. Commun. Image Represent"},{"key":"B3","first-page":"8765","article-title":"Debiased contrastive learning","volume":"33","author":"Chuang","year":"2020","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B4","first-page":"54","article-title":"\u201cZero-shot detection of AI-generated images,\u201d","volume-title":"European Conference on Computer Vision","author":"Cozzolino","year":"2024"},{"key":"B5","doi-asserted-by":"publisher","first-page":"10850","DOI":"10.1109\/TPAMI.2023.3261988","article-title":"Diffusion models in vision: a survey","volume":"45","author":"Croitoru","year":"2023","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B6","doi-asserted-by":"publisher","first-page":"336","DOI":"10.1016\/j.neucom.2012.09.042","article-title":"Multi-scale gray level co-occurrence matrices for texture description","volume":"120","author":"De Siqueira","year":"2013","journal-title":"Neurocomputing"},{"key":"B7","doi-asserted-by":"publisher","first-page":"6622","DOI":"10.3390\/app15126622","article-title":"Genconvit: deepfake video detection using generative convolutional vision transformer","volume":"15","author":"Deressa","year":"2025","journal-title":"Appl. Sci"},{"key":"B8","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume":"34","author":"Dhariwal","year":"2021","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B9","doi-asserted-by":"publisher","first-page":"6682","DOI":"10.1109\/TII.2022.3201572","article-title":"Securing facial bioinformation by eliminating adversarial perturbations","volume":"19","author":"Ding","year":"","journal-title":"IEEE Trans. Ind. Inf"},{"key":"B10","doi-asserted-by":"publisher","first-page":"2485","DOI":"10.1109\/LSP.2024.3438561","article-title":"Disrupting anti-spoofing systems by images of consistent identity","volume":"31","author":"Ding","year":"","journal-title":"IEEE Signal Process. Lett"},{"key":"B11","doi-asserted-by":"crossref","first-page":"0295","DOI":"10.11834\/jig.230088","article-title":"A survey of deepfake and related digital forensics","volume":"29","author":"Ding","year":"","journal-title":"J. Image Graph"},{"key":"B12","doi-asserted-by":"publisher","first-page":"7162","DOI":"10.1109\/TCYB.2022.3210294","article-title":"ExS-GAN: Synthesizing anti-forensics images via extra supervised GAN","volume":"53","author":"Ding","year":"","journal-title":"IEEE Trans. Cybern"},{"key":"B13","doi-asserted-by":"publisher","first-page":"3429","DOI":"10.1109\/TMM.2021.3098422","article-title":"Anti-forensics for face swapping videos via adversarial training","volume":"24","author":"Ding","year":"2021","journal-title":"IEEE Trans. Multimedia"},{"key":"B14","doi-asserted-by":"publisher","first-page":"881","DOI":"10.3390\/app15020881","article-title":"Detection of manipulations in digital images: a review of passive and active methods utilizing deep learning","volume":"15","author":"Duszejko","year":"2025","journal-title":"Appl. Sci"},{"key":"B15","first-page":"382","article-title":"\u201cOnline detection of AI-generated images,\u201d","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Epstein","year":"2023"},{"key":"B16","doi-asserted-by":"crossref","DOI":"10.1145\/3729233","article-title":"\u201cGenerating higher-quality anti-forensics deepfakes with adversarial sharpening mask,\u201d","volume-title":"ACM Transactions on Multimedia Computing, Communications and Applications","author":"Fan","year":"2025"},{"key":"B17","first-page":"4545","article-title":"\u201cSynthesizing black-box anti-forensics deepfakes with high visual quality,\u201d","volume-title":"ICASSP 2024-2024 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Fan","year":"2024"},{"key":"B18","doi-asserted-by":"crossref","first-page":"114","DOI":"10.1109\/MIPR59079.2023.00035","article-title":"\u201cAttacking identity semantics in deepfakes via deep feature fusion,\u201d","volume-title":"2023 IEEE 6th International Conference on Multimedia Information Processing and Retrieval (MIPR)","author":"Fan","year":"2023"},{"key":"B19","first-page":"80","article-title":"\u201cFake or jpeg? Revealing common biases in generated image detection datasets,\u201d","volume-title":"European Conference on Computer Vision","author":"Grommelt","year":"2025"},{"key":"B20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2503.06142","article-title":"Vlforgery face triad: detection, localization and attribution via multimodal large language models","author":"He","year":"2025","journal-title":"arXiv [preprint"},{"key":"B21","doi-asserted-by":"publisher","first-page":"8975","DOI":"10.1109\/ACCESS.2018.2890743","article-title":"Texture feature extraction methods: a survey","volume":"7","author":"Humeau-Heurtier","year":"2019","journal-title":"IEEE Access"},{"key":"B22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1710.10196","article-title":"Progressive growing of gans for improved quality, stability, and variation","author":"Karras","year":"2017","journal-title":"arXiv [preprint"},{"key":"B23","doi-asserted-by":"publisher","first-page":"307","DOI":"10.1561\/2200000056","article-title":"An introduction to variational autoencoders","volume":"12","author":"Kingma","year":"2019","journal-title":"Found. Trends Mach. Learn"},{"key":"B24","doi-asserted-by":"publisher","first-page":"10853","DOI":"10.1007\/s11042-017-5341-2","article-title":"A simple texture feature for retrieval of medical images","volume":"77","author":"Lan","year":"2018","journal-title":"Multimed. Tools Appl"},{"key":"B25","first-page":"1537","article-title":"\u201cFrequency-aware gan image detection via multi-scale fusion,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Li","year":"2022"},{"key":"B26","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2402.00045","article-title":"Detecting multimedia generated by large AI models: a survey","author":"Lin","year":"","journal-title":"arXiv [preprint"},{"key":"B27","first-page":"16815","article-title":"\u201cPreserving fairness generalization in deepfake detection,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Lin","year":""},{"key":"B28","first-page":"1","article-title":"\u201cDetection of diffusion model-generated faces by assessing smoothness and noise tolerance,\u201d","volume-title":"2024 IEEE International Symposium on Broadband Multimedia Systems and Broadcasting (BMSB)","author":"Liu","year":"2024"},{"key":"B29","first-page":"95","article-title":"\u201cDetecting generated images by real images,\u201d","volume-title":"European Conference on Computer Vision","author":"Liu","year":"2022"},{"key":"B30","first-page":"25435","article-title":"Seeing is not always believing: Benchmarking human and model perception of AI-generated images","volume":"36","author":"Lu","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst"},{"key":"B31","doi-asserted-by":"publisher","DOI":"10.1109\/AMLDS63918.2025.11159445","article-title":"\u201cSimple detection of AI-generated images based on noise correlation,\u201d","author":"Mallet","year":"2025","journal-title":"International conference on Advanced Machine Learning and Data Science (AMLDS)"},{"key":"B32","first-page":"100","article-title":"Texture analysis methods for medical image characterisation","volume":"75","author":"Nailon","year":"2010","journal-title":"Biomed. Imaging"},{"key":"B33","doi-asserted-by":"publisher","first-page":"971","DOI":"10.1109\/TPAMI.2002.1017623","article-title":"Multiresolution gray-scale and rotation invariant texture classification with local binary patterns","volume":"24","author":"Ojala","year":"2002","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell"},{"key":"B34","doi-asserted-by":"publisher","first-page":"24480","DOI":"10.1109\/CVPR52729.2023.02345","author":"Ojha","year":"2023"},{"key":"B35","first-page":"350","article-title":"A phase-aware framework for robust deepfake detection","volume":"18","author":"Qian","year":"2023","journal-title":"IEEE Trans. Inf. Forensics Secur"},{"key":"B36","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1109\/MSP.2017.2738401","article-title":"Deep multimodal learning:aA survey on recent advances and trends","volume":"34","author":"Ramachandram","year":"2017","journal-title":"IEEE Signal Process. Mag"},{"key":"B37","first-page":"28130","article-title":"\u201cRethinking the up-sampling operations in cnn-based generative network for generalizable deepfake detection,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Tan","year":"2024"},{"key":"B38","first-page":"8695","article-title":"\u201cCNN-generated images are surprisingly easy to spot... for now,\u201d","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision And Pattern Recognition","author":"Wang","year":"2020"},{"key":"B39","doi-asserted-by":"publisher","first-page":"39","DOI":"10.22215\/timreview\/1282","article-title":"The emergence of deepfake technology: a review","volume":"9","author":"Westerlund","year":"2019","journal-title":"Technol. Innov. Manag. Rev"},{"key":"B40","doi-asserted-by":"crossref","first-page":"392","DOI":"10.1109\/ICME.2012.87","article-title":"\u201cCamera model identification using local binary patterns,\u201d","volume-title":"2012 IEEE International Conference on Multimedia and Expo","author":"Xu","year":"2012"},{"key":"B41","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2406.09739","article-title":"Decoupling forgery semantics for generalizable deepfake detection","author":"Ye","year":"2024","journal-title":"arXiv [preprint"},{"key":"B42","first-page":"4010","article-title":"\u201cDetecting gan-synthesized faces using shallow CNN,\u201d","author":"Zhang","year":"2019","journal-title":"IEEE International Conference on Image Processing (ICIP)"},{"key":"B43","first-page":"1032","article-title":"\u201cMulti-modal deepfake detection with cross-modal attention,\u201d","volume-title":"Proceedings of the 29th ACM International Conference on Multimedia","author":"Zhao","year":"2021"},{"key":"B44","doi-asserted-by":"crossref","first-page":"169","DOI":"10.1145\/3577163.3595103","article-title":"\u201cExposing deepfakes using dual-channel network with multi-axis attention and frequency analysis,\u201d","volume-title":"Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security","author":"Zhou","year":"2023"},{"key":"B45","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2506.00874","article-title":"Breaking latent prior bias in detectors for generalizable aigc image detection","author":"Zhou","year":"2025","journal-title":"arXiv [preprint"},{"key":"B46","first-page":"1","article-title":"\u201cCGD-NET: a hybrid end-to-end network with gating decoding for liver tumor segmentation from ct images,\u201d","volume-title":"2024 IEEE International Conference on Advanced Video and Signal Based Surveillance (AVSS)","author":"Zhu","year":"2024"}],"container-title":["Frontiers in Artificial Intelligence"],"original-title":[],"link":[{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1663292\/full","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,22]],"date-time":"2025-10-22T05:32:35Z","timestamp":1761111155000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.frontiersin.org\/articles\/10.3389\/frai.2025.1663292\/full"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,22]]},"references-count":46,"alternative-id":["10.3389\/frai.2025.1663292"],"URL":"https:\/\/doi.org\/10.3389\/frai.2025.1663292","relation":{},"ISSN":["2624-8212"],"issn-type":[{"value":"2624-8212","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,22]]},"article-number":"1663292"}}