{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:55:06Z","timestamp":1781600106757,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":71,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,17]]},"DOI":"10.1145\/3785353.3815083","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:11:30Z","timestamp":1781597490000},"page":"241-252","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Seeing the Unseen: Enhancing Synthetic Video Detector Transferability to New AI Video Generation Models via Virtual Generators"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-9476-5915","authenticated-orcid":false,"given":"Danial","family":"Samadi Vahdati","sequence":"first","affiliation":[{"name":"Drexel University, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4139-9519","authenticated-orcid":false,"given":"Tai Duc","family":"Nguyen","sequence":"additional","affiliation":[{"name":"Electrical and Computer Engineering, Drexel University, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4075-9649","authenticated-orcid":false,"given":"Aref","family":"Azizpour","sequence":"additional","affiliation":[{"name":"College of Computing and Informatics, Drexel University, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9008-2034","authenticated-orcid":false,"given":"Hamed","family":"Ahangari","sequence":"additional","affiliation":[{"name":"ECE, Drexel University, Philadelphia, PA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3986-4039","authenticated-orcid":false,"given":"Matthew","family":"Stamm","sequence":"additional","affiliation":[{"name":"Drexel University, Philadelphia, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"e_1_3_3_1_2_2","unstructured":"[n. d.]. Meta AI. https:\/\/ai.meta.com\/. Accessed: 2025-09-18."},{"key":"e_1_3_3_1_3_2","first-page":"1","volume-title":"2018 IEEE international workshop on information forensics and security (WIFS)","author":"Afchar Darius","year":"2018","unstructured":"Darius Afchar, Vincent Nozick, Junichi Yamagishi, and Isao Echizen. 2018. Mesonet: a compact facial video forgery detection network. In 2018 IEEE international workshop on information forensics and security (WIFS). IEEE, 1\u20137."},{"key":"e_1_3_3_1_4_2","doi-asserted-by":"publisher","unstructured":"Mubarak Alrashoud. 2025. Deepfake video detection methods approaches and challenges. Alexandria Engineering Journal 125 (2025) 265\u2013277. 10.1016\/j.aej.2025.04.007","DOI":"10.1016\/j.aej.2025.04.007"},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"crossref","unstructured":"Irene Amerini Mauro Barni Sebastiano Battiato Paolo Bestagini Giulia Boato Vittoria Bruni Roberto Caldelli Francesco De\u00a0Natale Rocco De\u00a0Nicola Luca Guarnera et\u00a0al. 2025. Deepfake media forensics: Status and future challenges. Journal of Imaging 11 3 (2025) 73.","DOI":"10.3390\/jimaging11030073"},{"key":"e_1_3_3_1_6_2","first-page":"460","volume-title":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","author":"Bai Jianfa","year":"2024","unstructured":"Jianfa Bai, Man Lin, Gang Cao, and Zijie Lou. 2024. Ai-generated video detection via spatial-temporal anomaly learning. In Chinese Conference on Pattern Recognition and Computer Vision (PRCV). Springer, 460\u2013470."},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS49906.2020.9360905"},{"key":"e_1_3_3_1_8_2","unstructured":"Andreas Blattmann Tim Dockhorn Sumith Kulal Daniel Mendelevitch Maciej Kilian Dominik Lorenz Yam Levi Zion English Vikram Voleti Adam Letts Varun Jampani and Robin Rombach. 2023. Stable Video Diffusion: Scaling Latent Video Diffusion Models to Large Datasets. arxiv:https:\/\/arXiv.org\/abs\/2311.15127\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2311.15127"},{"key":"e_1_3_3_1_9_2","unstructured":"Haoxing Chen Yan Hong Zizheng Huang Zhuoer Xu Zhangxuan Gu Yaohui Li Jun Lan Huijia Zhu Jianfu Zhang Weiqiang Wang et\u00a0al. 2024. Demamba: Ai-generated video detection on million-scale genvideo benchmark. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.19707 (2024)."},{"key":"e_1_3_3_1_10_2","unstructured":"Haoxin Chen Menghan Xia Yingqing He Yong Zhang Xiaodong Cun Shaoshu Yang Jinbo Xing Yaofang Liu Qifeng Chen Xintao Wang et\u00a0al. 2023. Videocrafter1: Open diffusion models for high-quality video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2310.19512 (2023)."},{"key":"e_1_3_3_1_11_2","doi-asserted-by":"publisher","unstructured":"Iya Chivileva Philip Lynch Tom\u00e1s\u00a0E. Ward and Alan\u00a0F. Smeaton. 2024. A dataset of text prompts videos and video quality metrics from generative text-to-video AI models. Data in Brief 54 (2024) 110514. 10.1016\/j.dib.2024.110514","DOI":"10.1016\/j.dib.2024.110514"},{"key":"e_1_3_3_1_12_2","first-page":"1251","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Chollet Fran\u00e7ois","year":"2017","unstructured":"Fran\u00e7ois Chollet. 2017. Xception: Deep Learning with Depthwise Separable Convolutions. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 1251\u20131258."},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","unstructured":"Umur\u00a0Aybars Ciftci Ilke Demir and Lijun Yin. 2020. FakeCatcher: Detection of Synthetic Portrait Videos using Biological Signals. IEEE Transactions on Pattern Analysis and Machine Intelligence (2020) 1\u20131. 10.1109\/TPAMI.2020.3009287","DOI":"10.1109\/TPAMI.2020.3009287"},{"key":"e_1_3_3_1_14_2","doi-asserted-by":"crossref","unstructured":"Davide\u00a0Alessandro Coccomini Andrea Esuli Fabrizio Falchi Claudio Gennaro and Giuseppe Amato. 2024. Detecting images generated by diffusers. PeerJ Computer Science 10 (2024) e2127.","DOI":"10.7717\/peerj-cs.2127"},{"key":"e_1_3_3_1_15_2","first-page":"973","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Corvi Riccardo","year":"2023","unstructured":"Riccardo Corvi, Davide Cozzolino, Giovanni Poggi, Koki Nagano, and Luisa Verdoliva. 2023. Intriguing properties of synthetic images: from generative adversarial networks to diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 973\u2013982."},{"key":"e_1_3_3_1_16_2","first-page":"1","volume-title":"ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Corvi Riccardo","year":"2023","unstructured":"Riccardo Corvi, Davide Cozzolino, Giada Zingarini, Giovanni Poggi, Koki Nagano, and Luisa Verdoliva. 2023. On the detection of synthetic images generated by diffusion models. In ICASSP 2023-2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 1\u20135."},{"key":"e_1_3_3_1_17_2","doi-asserted-by":"crossref","first-page":"5297","DOI":"10.1109\/ICIP.2014.7026072","volume-title":"2014 IEEE International Conference on Image Processing (ICIP)","author":"Cozzolino Davide","year":"2014","unstructured":"Davide Cozzolino, Diego Gragnaniello, and Luisa Verdoliva. 2014. Image forgery detection through residual-based local descriptors and block-matching. In 2014 IEEE International Conference on Image Processing (ICIP). 5297\u20135301. 10.1109\/ICIP.2014.7026072"},{"key":"e_1_3_3_1_18_2","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Cubuk Ekin\u00a0D.","year":"2019","unstructured":"Ekin\u00a0D. Cubuk, Barret Zoph, Dandelion Mane, Vijay Vasudevan, and Quoc\u00a0V. Le. 2019. AutoAugment: Learning Augmentation Strategies From Data. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_1_19_2","volume-title":"Forty-first International Conference on Machine Learning","author":"Esser Patrick","year":"2024","unstructured":"Patrick Esser, Sumith Kulal, Andreas Blattmann, Rahim Entezari, Jonas M\u00fcller, Harry Saini, Yam Levi, Dominik Lorenz, Axel Sauer, Frederic Boesel, Dustin Podell, Tim Dockhorn, Zion English, and Robin Rombach. 2024. Scaling Rectified Flow Transformers for High-Resolution Image Synthesis. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=FPnUhsQJ5B"},{"key":"e_1_3_3_1_20_2","first-page":"659","volume-title":"34th British Machine Vision Conference 2023, BMVC 2023, Aberdeen, UK, November 20-24, 2023","author":"Fang Shengbang","year":"2023","unstructured":"Shengbang Fang, Tai\u00a0D. Nguyen, and Matthew\u00a0C. Stamm. 2023. Open Set Synthetic Image Source Attribution. In 34th British Machine Vision Conference 2023, BMVC 2023, Aberdeen, UK, November 20-24, 2023. BMVA Press, 659. http:\/\/proceedings.bmvc2023.org\/659\/"},{"key":"e_1_3_3_1_21_2","doi-asserted-by":"crossref","DOI":"10.7551\/mitpress\/10451.001.0001","volume-title":"Photo forensics","author":"Farid Hany","year":"2016","unstructured":"Hany Farid. 2016. Photo forensics. MIT press."},{"key":"e_1_3_3_1_22_2","unstructured":"Genmo Team. 2024. Mochi 1. https:\/\/github.com\/genmoai\/mochi."},{"key":"e_1_3_3_1_23_2","volume-title":"Digital image processing","author":"Gonzalez Rafael\u00a0C","year":"2009","unstructured":"Rafael\u00a0C Gonzalez. 2009. Digital image processing. Pearson education india."},{"key":"e_1_3_3_1_24_2","doi-asserted-by":"crossref","unstructured":"Diego Gragnaniello Davide Cozzolino Francesco Marra Giovanni Poggi and Luisa Verdoliva. 2021. Are GAN generated images easy to detect? A critical analysis of the state-of-the-art. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2104.02617 (2021).","DOI":"10.1109\/ICME51207.2021.9428429"},{"key":"e_1_3_3_1_25_2","doi-asserted-by":"crossref","unstructured":"Bahadir\u00a0K Gunturk John Glotzbach Yucel Altunbasak Ronald\u00a0W Schafer and Russel\u00a0M Mersereau. 2005. Demosaicking: color filter array interpolation. IEEE Signal processing magazine 22 1 (2005) 44\u201354.","DOI":"10.1109\/MSP.2005.1407714"},{"key":"e_1_3_3_1_26_2","unstructured":"Yoav HaCohen Nisan Chiprut Benny Brazowski Daniel Shalem Dudu Moshe Eitan Richardson Eran Levin Guy Shiran Nir Zabari Ori Gordon et\u00a0al. 2024. Ltx-video: Realtime video latent diffusion. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2501.00103 (2024)."},{"key":"e_1_3_3_1_27_2","first-page":"770","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 770\u2013778."},{"key":"e_1_3_3_1_28_2","unstructured":"Dan Hendrycks Norman Mu Ekin\u00a0D Cubuk Barret Zoph Justin Gilmer and Balaji Lakshminarayanan. 2019. Augmix: A simple data processing method to improve robustness and uncertainty. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1912.02781 (2019)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"crossref","unstructured":"Jonathan Ho Tim Salimans Alexey Gritsenko William Chan Mohammad Norouzi and David\u00a0J Fleet. 2022. Video diffusion models. Advances in neural information processing systems 35 (2022) 8633\u20138646.","DOI":"10.52202\/068431-0628"},{"key":"e_1_3_3_1_30_2","unstructured":"Wenyi Hong Ming Ding Wendi Zheng Xinghan Liu and Jie Tang. 2022. CogVideo: Large-scale Pretraining for Text-to-Video Generation via Transformers. arxiv:https:\/\/arXiv.org\/abs\/2205.15868\u00a0[cs.CV] https:\/\/arxiv.org\/abs\/2205.15868"},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","unstructured":"Brian Hosler Owen Mayer Xinwei Zhao Chen Chen James Shackleford and Matthew Stamm. 2019. Video-ACID. 10.21227\/4dzb-h573","DOI":"10.21227\/4dzb-h573"},{"key":"e_1_3_3_1_32_2","unstructured":"Anil\u00a0K Jain. 1989. Fundamentals of digital image processing. (1989)."},{"key":"e_1_3_3_1_33_2","first-page":"8110","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and improving the image quality of stylegan. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 8110\u20138119."},{"key":"e_1_3_3_1_34_2","doi-asserted-by":"crossref","unstructured":"Jihwan Kim Junoh Kang Jinyoung Choi and Bohyung Han. 2024. Fifo-diffusion: Generating infinite videos from text without training. Advances in Neural Information Processing Systems 37 (2024) 89834\u201389868.","DOI":"10.52202\/079017-2853"},{"key":"e_1_3_3_1_35_2","first-page":"28050","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Kundu Rohit","year":"2025","unstructured":"Rohit Kundu, Hao Xiong, Vishal Mohanty, Athula Balachandran, and Amit\u00a0K Roy-Chowdhury. 2025. Towards a universal synthetic video detector: From face or background manipulations to fully ai-generated content. In Proceedings of the Computer Vision and Pattern Recognition Conference. 28050\u201328060."},{"key":"e_1_3_3_1_36_2","first-page":"5001","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Li Lingzhi","year":"2020","unstructured":"Lingzhi Li, Jianmin Bao, Ting Zhang, Hao Yang, Dong Chen, Fang Wen, and Baining Guo. 2020. Face x-ray for more general face forgery detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 5001\u20135010."},{"key":"e_1_3_3_1_37_2","first-page":"489","volume-title":"Visual Communications and Image Processing 2008","author":"Li Xin","year":"2008","unstructured":"Xin Li, Bahadir Gunturk, and Lei Zhang. 2008. Image demosaicing: A systematic survey. In Visual Communications and Image Processing 2008 , Vol.\u00a06822. SPIE, 489\u2013503."},{"key":"e_1_3_3_1_38_2","volume-title":"CVPRW","author":"Li Yuezun","year":"2018","unstructured":"Yuezun Li and Siwei Lyu. 2018. Exposing deepfake videos by detecting face warping artifacts. In CVPRW."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"crossref","unstructured":"Li Lin Neeraj Gupta Yue Zhang Hainan Ren Chun-Hao Liu Feng Ding Xin Wang Xin Li Luisa Verdoliva and Shu Hu. 2024. Detecting multimedia generated by large ai models: A survey. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.00045 (2024).","DOI":"10.36227\/techrxiv.170723324.44685515\/v1"},{"key":"e_1_3_3_1_40_2","first-page":"360","volume-title":"European Conference on Computer Vision","author":"Liu Shaowei","year":"2024","unstructured":"Shaowei Liu, Zhongzheng Ren, Saurabh Gupta, and Shenlong Wang. 2024. Physgen: Rigid-body physics-grounded image-to-video generation. In European Conference on Computer Vision. Springer, 360\u2013378."},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","unstructured":"Yun Liu Zuliang Wan Xiaohua Yin Guanghui Yue Aiping Tan and Zhi Zheng. 2023. Detection of GAN generated image using color gradient representation. Journal of Visual Communication and Image Representation 95 (2023) 103876. 10.1016\/j.jvcir.2023.103876","DOI":"10.1016\/j.jvcir.2023.103876"},{"key":"e_1_3_3_1_42_2","first-page":"10012","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Liu Ze","year":"2021","unstructured":"Ze Liu, Yutong Lin, Yue Cao, Han Hu, Yixuan Wei, Zheng Zhang, Stephen Lin, and Baining Guo. 2021. Swin transformer: Hierarchical vision transformer using shifted windows. In Proceedings of the IEEE\/CVF international conference on computer vision. 10012\u201310022."},{"key":"e_1_3_3_1_43_2","unstructured":"Luma AI. 2025. Luma AI. https:\/\/lumalabs.ai\/. Accessed: 2025-09-01."},{"key":"e_1_3_3_1_44_2","unstructured":"Xin Ma Yaohui Wang Gengyun Jia Xinyuan Chen Yuan-Fang Li Cunjian Chen and Yu Qiao. 2024. Cinemo: Consistent and controllable image animation with motion diffusion models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2407.15642 (2024)."},{"key":"e_1_3_3_1_45_2","volume-title":"A Wavelet Tour of Signal Processing: The Sparse Way (3rd ed.)","author":"Mallat St\u00e9phane","year":"2009","unstructured":"St\u00e9phane Mallat. 2009. A Wavelet Tour of Signal Processing: The Sparse Way (3rd ed.). Academic Press."},{"key":"e_1_3_3_1_46_2","doi-asserted-by":"crossref","first-page":"2659","DOI":"10.1109\/ICASSP.2014.6854082","volume-title":"2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)","author":"Milani Simone","year":"2014","unstructured":"Simone Milani, Paolo Bestagini, Marco Tagliasacchi, and Stefano Tubaro. 2014. Demosaicing strategy identification via eigenalgorithms. In 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP). IEEE, 2659\u20132663."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"crossref","unstructured":"Ben Mildenhall Pratul\u00a0P Srinivasan Matthew Tancik Jonathan\u00a0T Barron Ravi Ramamoorthi and Ren Ng. 2021. Nerf: Representing scenes as neural radiance fields for view synthesis. Commun. ACM 65 1 (2021) 99\u2013106.","DOI":"10.1145\/3503250"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"crossref","unstructured":"Mathew Monfort Alex Andonian Bolei Zhou Kandan Ramakrishnan Sarah\u00a0Adel Bargal Tom Yan Lisa Brown Quanfu Fan Dan Gutfreund Carl Vondrick et\u00a0al. 2019. Moments in time dataset: one million videos for event understanding. IEEE transactions on pattern analysis and machine intelligence 42 2 (2019) 502\u2013508.","DOI":"10.1109\/TPAMI.2019.2901464"},{"key":"e_1_3_3_1_49_2","unstructured":"Lakshmanan Nataraj Tajuddin\u00a0Manhar Mohammed Shivkumar Chandrasekaran Arjuna Flenner Jawadul\u00a0H. Bappy Amit\u00a0K. Roy-Chowdhury and B.\u00a0S. Manjunath. 2019. Detecting GAN generated Fake Images using Co-occurrence Matrices. Electronic Imaging (2019). https:\/\/arxiv.org\/abs\/1903.06836"},{"key":"e_1_3_3_1_50_2","first-page":"1","volume-title":"2019 IEEE 10th international conference on biometrics theory, applications and systems (BTAS)","author":"Nguyen Huy\u00a0H","year":"2019","unstructured":"Huy\u00a0H Nguyen, Fuming Fang, Junichi Yamagishi, and Isao Echizen. 2019. Multi-task learning for detecting and segmenting manipulated facial images and videos. In 2019 IEEE 10th international conference on biometrics theory, applications and systems (BTAS). IEEE, 1\u20138."},{"key":"e_1_3_3_1_51_2","first-page":"3040","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Nguyen Tai\u00a0D","year":"2025","unstructured":"Tai\u00a0D Nguyen, Aref Azizpour, and Matthew\u00a0C Stamm. 2025. Forensic self-descriptions are all you need for zero-shot detection, open-set source attribution, and clustering of ai-generated images. In Proceedings of the Computer Vision and Pattern Recognition Conference. 3040\u20133050."},{"key":"e_1_3_3_1_52_2","first-page":"24480","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Ojha Utkarsh","year":"2023","unstructured":"Utkarsh Ojha, Yuheng Li, and Yong\u00a0Jae Lee. 2023. Towards universal fake image detectors that generalize across generative models. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 24480\u201324489."},{"key":"e_1_3_3_1_53_2","volume-title":"Sora: Creating video from text","year":"2025","unstructured":"OpenAI. 2025. Sora: Creating video from text. https:\/\/openai.com\/index\/sora\/ Accessed: 2025-09-05."},{"key":"e_1_3_3_1_54_2","volume-title":"Signals & Systems (2nd ed.)","author":"Oppenheim Alan\u00a0V","year":"1997","unstructured":"Alan\u00a0V Oppenheim, Alan\u00a0S Willsky, and S\u00a0Hamid Nawab. 1997. Signals & Systems (2nd ed.). Prentice Hall."},{"key":"e_1_3_3_1_55_2","doi-asserted-by":"publisher","unstructured":"Daeeol Park Hyunsik Na and Daeseon Choi. 2024. Performance Comparison and Visualization of AI-Generated-Image Detection Methods. IEEE Access 12 (2024) 62609\u201362627. 10.1109\/ACCESS.2024.3394250","DOI":"10.1109\/ACCESS.2024.3394250"},{"key":"e_1_3_3_1_56_2","first-page":"8245","volume-title":"Proceedings of the Computer Vision and Pattern Recognition Conference","author":"Park Jeongsoo","year":"2025","unstructured":"Jeongsoo Park and Andrew Owens. 2025. Community forensics: Using thousands of generators to train fake image detectors. In Proceedings of the Computer Vision and Pattern Recognition Conference. 8245\u20138257."},{"key":"e_1_3_3_1_57_2","doi-asserted-by":"crossref","unstructured":"Shavez\u00a0Mushtaq Qureshi Atif Saeed Sultan\u00a0H Almotiri Farooq Ahmad and Mohammed\u00a0A Al\u00a0Ghamdi. 2024. Deepfake forensics: a survey of digital forensic methods for multimodal deepfake identification on social media. PeerJ Computer Science 10 (2024) e2037.","DOI":"10.7717\/peerj-cs.2037"},{"key":"e_1_3_3_1_58_2","doi-asserted-by":"publisher","unstructured":"Surbhi Raj Jimson Mathew and Arijit Mondal. 2024. Generalized and robust model for GAN-generated image detection. Pattern Recognition Letters 182 (2024) 104\u2013110. 10.1016\/j.patrec.2024.04.018","DOI":"10.1016\/j.patrec.2024.04.018"},{"key":"e_1_3_3_1_59_2","first-page":"10684","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-resolution image synthesis with latent diffusion models. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 10684\u201310695."},{"key":"e_1_3_3_1_60_2","first-page":"234","volume-title":"International Conference on Medical image computing and computer-assisted intervention","author":"Ronneberger Olaf","year":"2015","unstructured":"Olaf Ronneberger, Philipp Fischer, and Thomas Brox. 2015. U-net: Convolutional networks for biomedical image segmentation. In International Conference on Medical image computing and computer-assisted intervention. Springer, 234\u2013241."},{"key":"e_1_3_3_1_61_2","first-page":"28130","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Tan Chuangchuang","year":"2024","unstructured":"Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, and Yunchao Wei. 2024. Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 28130\u201328139."},{"key":"e_1_3_3_1_62_2","doi-asserted-by":"publisher","unstructured":"Diangarti Tariang Riccardo Corvi Davide Cozzolino Giovanni Poggi Koki Nagano and Luisa Verdoliva. 2024. Synthetic Image Verification in the Era of Generative Artificial Intelligence: What Works and What Isn\u2019t There yet. IEEE Security & Privacy 22 3 (2024) 37\u201349. 10.1109\/MSEC.2024.3376637","DOI":"10.1109\/MSEC.2024.3376637"},{"key":"e_1_3_3_1_63_2","first-page":"4397","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops","author":"Vahdati Danial\u00a0Samadi","year":"2024","unstructured":"Danial\u00a0Samadi Vahdati, Tai\u00a0D. Nguyen, Aref Azizpour, and Matthew\u00a0C. Stamm. 2024. Beyond Deepfake Images: Detecting AI-Generated Videos. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops. 4397\u20134408."},{"key":"e_1_3_3_1_64_2","doi-asserted-by":"crossref","unstructured":"Danial\u00a0Samadi Vahdati and Matthew\u00a0C Stamm. 2023. Detecting gan-generated synthetic images using semantic inconsistencies. Electronic Imaging 35 (2023) 1\u20136.","DOI":"10.2352\/EI.2023.35.4.MWSF-380"},{"key":"e_1_3_3_1_65_2","doi-asserted-by":"crossref","first-page":"1187","DOI":"10.1109\/ICME55011.2023.00207","volume-title":"2023 IEEE International Conference on Multimedia and Expo (ICME)","author":"Wang Huaming","year":"2023","unstructured":"Huaming Wang, Jianwei Fei, Yunshu Dai, Lingyun Leng, and Zhihua Xia. 2023. General GAN-generated image detection by data augmentation in fingerprint domain. In 2023 IEEE International Conference on Multimedia and Expo (ICME). IEEE, 1187\u20131192."},{"key":"e_1_3_3_1_66_2","doi-asserted-by":"crossref","first-page":"615","DOI":"10.1145\/3512527.3531415","volume-title":"Proceedings of the 2022 international conference on multimedia retrieval","author":"Wang Junke","year":"2022","unstructured":"Junke Wang, Zuxuan Wu, Wenhao Ouyang, Xintong Han, Jingjing Chen, Yu-Gang Jiang, and Ser-Nam Li. 2022. M2tr: Multi-modal multi-scale transformers for deepfake detection. In Proceedings of the 2022 international conference on multimedia retrieval. 615\u2013623."},{"key":"e_1_3_3_1_67_2","doi-asserted-by":"publisher","unstructured":"Ruoyu Wang Shaowei Wang Rui Gong Chen Cai Jianjun Gao Wenqian Wang Wenyang Liu and Kim-Hui Yap. 2026. MotionAnimate: Animate human images with pose motion for vivid and temporally consistent video generation. Information Fusion 126 (2026) 103559. 10.1016\/j.inffus.2025.103559","DOI":"10.1016\/j.inffus.2025.103559"},{"key":"e_1_3_3_1_68_2","first-page":"8695","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Wang Sheng-Yu","year":"2020","unstructured":"Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, and Alexei\u00a0A Efros. 2020. CNN-generated images are surprisingly easy to spot... for now. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 8695\u20138704."},{"key":"e_1_3_3_1_69_2","first-page":"22445","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Wang Zhendong","year":"2023","unstructured":"Zhendong Wang, Jianmin Bao, Wengang Zhou, Weilun Wang, Hezhen Hu, Hong Chen, and Houqiang Li. 2023. Dire for diffusion-generated image detection. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 22445\u201322455."},{"key":"e_1_3_3_1_70_2","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS47025.2019.9035107"},{"key":"e_1_3_3_1_71_2","first-page":"70","volume-title":"International Conference on Pattern Recognition","author":"Zhao Xinwei","year":"2022","unstructured":"Xinwei Zhao and Matthew\u00a0C Stamm. 2022. Making generated images hard to spot: A transferable attack on synthetic image detectors. In International Conference on Pattern Recognition. Springer, 70\u201384."},{"key":"e_1_3_3_1_72_2","unstructured":"Zangwei Zheng Xiangyu Peng Tianji Yang Chenhui Shen Shenggui Li Hongxin Liu Yukun Zhou Tianyi Li and Yang You. 2024. Open-Sora: Democratizing Efficient Video Production for All. https:\/\/arxiv.org\/abs\/2412.20404. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2412.20404 (2024). https:\/\/github.com\/hpcaitech\/Open-Sora Open-source video generation model: code weights and training\/inference pipeline publicly released."}],"event":{"name":"IH&MMSec '26: ACM Workshop on Information Hiding and Multimedia Security","location":"Firenze Italy","acronym":"IH&MMSec '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 ACM Workshop on Information Hiding and Multimedia Security"],"original-title":[],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:21:31Z","timestamp":1781598091000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785353.3815083"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":71,"alternative-id":["10.1145\/3785353.3815083","10.1145\/3785353"],"URL":"https:\/\/doi.org\/10.1145\/3785353.3815083","relation":{},"subject":[],"published":{"date-parts":[[2026,6,16]]},"assertion":[{"value":"2026-06-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}