{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T18:48:45Z","timestamp":1775069325813,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":75,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755707","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T06:56:44Z","timestamp":1761375404000},"page":"11667-11676","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["SpecXNet: A Dual-Domain Convolutional Network for Robust Deepfake Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-6564-4867","authenticated-orcid":false,"given":"Inzamamul","family":"Alam","sequence":"first","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-9405-5684","authenticated-orcid":false,"given":"Md Tanvir","family":"Islam","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8983-1542","authenticated-orcid":false,"given":"Simon S.","family":"Woo","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Engineering, Sungkyunkwan University, Suwon, Republic of Korea"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_2_1_1","unstructured":"Danbooru AI. 2021. DanBooru Dataset. https:\/\/gwern.net\/danbooru2021 [Accessed on 12-04-2025]."},{"key":"e_1_3_2_2_2_1","first-page":"849","volume-title":"Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal. In Companion Proceedings of the ACM on Web Conference","author":"Alam Inzamamul","year":"2025","unstructured":"Inzamamul Alam, Md Tanvir Islam, and Simon S Woo. 2025a. Saliency-Aware Diffusion Reconstruction for Effective Invisible Watermark Removal. In Companion Proceedings of the ACM on Web Conference 2025. 849-853."},{"key":"e_1_3_2_2_3_1","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Alam Inzamamul","year":"2025","unstructured":"Inzamamul Alam, Md Tanvir Islam, Simon S. Woo, and Khan Muhammad. 2025b. SpecGuard: Spectral Projection-based Advanced Invisible Watermarking. In Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_2_4_1","doi-asserted-by":"publisher","DOI":"10.1145\/3627673.3680085"},{"key":"e_1_3_2_2_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27829"},{"key":"e_1_3_2_2_6_1","volume-title":"DA-FDFtNet: dual attention fake detection fine-tuning network to detect various AI-generated fake images. arXiv preprint arXiv:2112.12001","author":"Bang Young Oh","year":"2021","unstructured":"Young Oh Bang and Simon S Woo. 2021. DA-FDFtNet: dual attention fake detection fine-tuning network to detect various AI-generated fake images. arXiv preprint arXiv:2112.12001 (2021)."},{"key":"e_1_3_2_2_7_1","volume-title":"Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096","author":"Brock Andrew","year":"2018","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2018. Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"e_1_3_2_2_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01565"},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19784-0_39"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.52202\/079017-3218"},{"key":"e_1_3_2_2_13_1","volume-title":"Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 4530-4537","author":"Cho Beomsang","year":"2023","unstructured":"Beomsang Cho, Binh M Le, Jiwon Kim, Simon Woo, Shahroz Tariq, Alsharif Abuadbba, and Kristen Moore. 2023. Towards understanding of deepfake videos in the wild. In Proceedings of the 32nd ACM International Conference on Information and Knowledge Management. 4530-4537."},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00112"},{"key":"e_1_3_2_2_15_1","first-page":"687","article-title":"Fakecatcher: detection of synthetic portrait videos using biological signals","volume":"11","author":"Ciftci Umur Aybars","year":"2023","unstructured":"Umur Aybars Ciftci, Ilke Demir, and Lijun Yin. 2023. Fakecatcher: detection of synthetic portrait videos using biological signals. US Patent 11,687,778.","journal-title":"US Patent"},{"key":"e_1_3_2_2_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00104"},{"key":"e_1_3_2_2_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095167"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP53242.2021.9675329"},{"key":"e_1_3_2_2_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00439"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"e_1_3_2_2_21_1","volume-title":"Diffusion models beat gans on image synthesis. Advances in neural information processing systems","author":"Dhariwal Prafulla","year":"2021","unstructured":"Prafulla Dhariwal and Alexander Nichol. 2021. Diffusion models beat gans on image synthesis. Advances in neural information processing systems, Vol. 34 (2021), 8780-8794."},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"e_1_3_2_2_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICME51207.2021.9428429"},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652027"},{"key":"e_1_3_2_2_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_2_26_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840-6851."},{"key":"e_1_3_2_2_27_1","unstructured":"David Holz. 2022 July 12. Midjourney: Expanding the Imaginative Powers. https:\/\/www.midjourney.com\/home [Accessed on 12-04-2025]."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i19.30107"},{"key":"e_1_3_2_2_29_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.aej.2024.12.031"},{"key":"e_1_3_2_2_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00163"},{"key":"e_1_3_2_2_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58201-2_28"},{"key":"e_1_3_2_2_32_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i1.19990"},{"key":"e_1_3_2_2_33_1","volume-title":"Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196","author":"Karras Tero","year":"2017","unstructured":"Tero Karras, Timo Aila, Samuli Laine, and Jaakko Lehtinen. 2017. Progressive growing of gans for improved quality, stability, and variation. arXiv preprint arXiv:1710.10196 (2017)."},{"key":"e_1_3_2_2_34_1","volume-title":"Training generative adversarial networks with limited data. Advances in neural information processing systems","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Miika Aittala, Janne Hellsten, Samuli Laine, Jaakko Lehtinen, and Timo Aila. 2020a. Training generative adversarial networks with limited data. Advances in neural information processing systems, Vol. 33 (2020), 12104-12114."},{"key":"e_1_3_2_2_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00336"},{"key":"e_1_3_2_2_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2023.3348450"},{"key":"e_1_3_2_2_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3652583.3658035"},{"key":"e_1_3_2_2_39_1","unstructured":"Konwoo Kim Michael Laskin Igor Mordatch and Deepak Pathak. 2021. How to adapt your large-scale vision-and-language model. (2021)."},{"key":"e_1_3_2_2_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00381"},{"key":"e_1_3_2_2_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3595353.3595882"},{"key":"e_1_3_2_2_42_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_2_43_1","volume-title":"Exposing the fake: Effective diffusion-generated images detection. arXiv preprint arXiv:2307.06272","author":"Ma Ruipeng","year":"2023","unstructured":"Ruipeng Ma, Jinhao Duan, Fei Kong, Xiaoshuang Shi, and Kaidi Xu. 2023. Exposing the fake: Effective diffusion-generated images detection. arXiv preprint arXiv:2307.06272 (2023)."},{"key":"e_1_3_2_2_44_1","volume-title":"Tailor made AI","author":"Author","year":"2019","unstructured":"Author: Tailor made AI. 2019, November. Yijian: Chinese AI Painting Creative Cloud. https:\/\/creator.nightcafe.studio\/ [Accessed on 12-04-2025]."},{"key":"e_1_3_2_2_45_1","volume-title":"Dreambooth: Tailor-made AI Image Generation. https:\/\/www.astria.ai\/ [Accessed on 12-04-2025].","author":"Tailor","year":"2022","unstructured":"Tailor made AI. 2022. Dreambooth: Tailor-made AI Image Generation. https:\/\/www.astria.ai\/ [Accessed on 12-04-2025]."},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3179116"},{"key":"e_1_3_2_2_47_1","volume-title":"The creation and detection of deepfakes: A survey. ACM computing surveys (CSUR)","author":"Mirsky Yisroel","year":"2021","unstructured":"Yisroel Mirsky and Wenke Lee. 2021. The creation and detection of deepfakes: A survey. ACM computing surveys (CSUR), Vol. 54, 1 (2021), 1-41."},{"key":"e_1_3_2_2_48_1","unstructured":"Emad Mostaque. 2022. Stability.ai: Stable Diffusion Public Release. https:\/\/stability.ai\/blog\/stable-diffusion-public-release [Accessed on 12-04-2025]."},{"key":"e_1_3_2_2_49_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103525"},{"key":"e_1_3_2_2_50_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681672"},{"key":"e_1_3_2_2_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"e_1_3_2_2_52_1","unstructured":"Or Patashnik Rinon Gal Haggai Maron Gal Chechik and Daniel Cohen-Or. 2021. StyleGAN-NADA: CLIP-Guided Domain Adaptation of Image Generators. arXiv:2108.00946 [cs.CV]"},{"key":"e_1_3_2_2_53_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3809-3817","author":"Pellicer Alvaro Lopez","year":"2024","unstructured":"Alvaro Lopez Pellicer, Yi Li, and Plamen Angelov. 2024. PUDD: towards robust multi-modal prototype-based deepfake detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 3809-3817."},{"key":"e_1_3_2_2_54_1","volume-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952","author":"Podell Dustin","year":"2023","unstructured":"Dustin Podell, Zion English, Kyle Lacey, Andreas Blattmann, Tim Dockhorn, Jonas M\u00fcller, Joe Penna, and Robin Rombach. 2023. Sdxl: Improving latent diffusion models for high-resolution image synthesis. arXiv preprint arXiv:2307.01952 (2023)."},{"key":"e_1_3_2_2_55_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_2_56_1","unstructured":"Aditya Ramesh Mikhail Pavlov Gabriel Goh Scott Gray Alec Radford Mark Chen and Ilya Sutskever. 2022. DALL-E 2. arXiv:2201.03994"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_2_59_1","unstructured":"Angus Russell. 2019 November. Nightcafe: Create Amazing Artworks using the Power of Artificial Intelligence. https:\/\/creator.nightcafe.studio\/ [Accessed on 12-04-2025]."},{"key":"e_1_3_2_2_60_1","volume-title":"International conference on machine learning. pmlr, 2256-2265","author":"Sohl-Dickstein Jascha","year":"2015","unstructured":"Jascha Sohl-Dickstein, Eric Weiss, Niru Maheswaranathan, and Surya Ganguli. 2015. Deep unsupervised learning using nonequilibrium thermodynamics. In International conference on machine learning. pmlr, 2256-2265."},{"key":"e_1_3_2_2_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"e_1_3_2_2_62_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3554779"},{"key":"e_1_3_2_2_63_1","volume-title":"DiffusionDB: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2302.08113","author":"Wang Chenyang","year":"2023","unstructured":"Chenyang Wang, Xuehai Liu, Han Zhang, Yaxin Wang, Yiming Sheng, Lu Yuan, Jun-Yan Zhu, and Lujia Yang. 2023b. DiffusionDB: A large-scale prompt gallery dataset for text-to-image generative models. arXiv preprint arXiv:2302.08113 (2023)."},{"key":"e_1_3_2_2_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"e_1_3_2_2_65_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"e_1_3_2_2_66_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00253"},{"key":"e_1_3_2_2_67_1","volume-title":"Generalizable synthetic image detection via language-guided contrastive learning. arXiv preprint arXiv:2305.13800","author":"Wu Haiwei","year":"2023","unstructured":"Haiwei Wu, Jiantao Zhou, and Shile Zhang. 2023. Generalizable synthetic image detection via language-guided contrastive learning. arXiv preprint arXiv:2305.13800 (2023)."},{"key":"e_1_3_2_2_68_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"e_1_3_2_2_69_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547913"},{"key":"e_1_3_2_2_70_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10221905"},{"key":"e_1_3_2_2_71_1","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"e_1_3_2_2_72_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3688984"},{"key":"e_1_3_2_2_73_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"e_1_3_2_2_74_1","first-page":"77771","article-title":"Genimage: A million-scale benchmark for detecting ai-generated image","volume":"36","author":"Zhu Mingjian","year":"2023","unstructured":"Mingjian Zhu, Hanting Chen, Qiangyu Yan, Xudong Huang, Guanyu Lin, Wei Li, Zhijun Tu, Hailin Hu, Jie Hu, and Yunhe Wang. 2023a. Genimage: A million-scale benchmark for detecting ai-generated image. Advances in Neural Information Processing Systems, Vol. 36 (2023), 77771-77782.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_2_75_1","volume-title":"StyleGAN3: generative networks for improving the equivariance of translation and rotation. arXiv preprint arXiv:2307.03898","author":"Zhu Tianlei","year":"2023","unstructured":"Tianlei Zhu, Junqi Chen, Renzhe Zhu, and Gaurav Gupta. 2023b. StyleGAN3: generative networks for improving the equivariance of translation and rotation. arXiv preprint arXiv:2307.03898 (2023)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","location":"Dublin Ireland","acronym":"MM '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755707","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T19:35:44Z","timestamp":1765308944000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755707"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":75,"alternative-id":["10.1145\/3746027.3755707","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755707","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}