{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T16:40:23Z","timestamp":1786120823964,"version":"build-2736575974"},"publisher-location":"New York, NY, USA","reference-count":64,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,8,8]],"date-time":"2026-08-08T00:00:00Z","timestamp":1786147200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"National Natural Science Foundation of China","award":["62402273"],"award-info":[{"award-number":["62402273"]}]},{"name":"Fundamental and Interdisciplinary Disciplines Breakthrough Plan of the Ministry of Education of China","award":["JYB2025XDXM114"],"award-info":[{"award-number":["JYB2025XDXM114"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,8,9]]},"DOI":"10.1145\/3770855.3817509","type":"proceedings-article","created":{"date-parts":[[2026,8,6]],"date-time":"2026-08-06T17:15:37Z","timestamp":1786036537000},"page":"9326-9337","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["FakeI2V-Bench: Benchmarking the Applicability of Image-level Deepfake Detectors for Deepfake Video Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-9002-7930","authenticated-orcid":false,"given":"Pei","family":"Li","sequence":"first","affiliation":[{"name":"School of Cyber Science and Technology, Shandong University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-0176-9782","authenticated-orcid":false,"given":"Sihan","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Cyber Science and Technology, Shandong University, Qingdao, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-2630-2680","authenticated-orcid":false,"given":"Delong","family":"Ran","sequence":"additional","affiliation":[{"name":"Institute for Network Sciences and Cyberspace, BNRist, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3189-8223","authenticated-orcid":false,"given":"Tianshuo","family":"Cong","sequence":"additional","affiliation":[{"name":"School of Cryptologic Science and Engineering, Shandong University, Jinan, Shandong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,8,8]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Springer European Conference on Computer Vision (ECCV).","author":"Baraldi Lorenzo","year":"2024","unstructured":"Lorenzo Baraldi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, Alessandro Nicolosi, and Rita Cucchiara. 2024. Contrasting Deepfakes Diffusion via Contrastive Learning and Global-Local Similarities. In Springer European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_2_1","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 Preprint 2311.15127. arXiv:2311.15127 https:\/\/arxiv.org\/abs\/2311.15127"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the National Academy of Sciences, V121","author":"Bohacek Matyas","year":"2024","unstructured":"Matyas Bohacek and Hany Farid. 2024. The making of an AI news anchor\u2014and its implications. Proceedings of the National Academy of Sciences, V121, 1 (2024), e2315678121."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1010933404324"},{"key":"e_1_3_2_1_5_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_1_6_1","unstructured":"Tim Brooks Bill Peebles Connor Holmes Will DePue Yufei Guo Li Jing David Schnurr Joe Taylor Troy Luhman Eric Luhman Clarence Ng Ricky Wang and Aditya Ramesh. 2024. Video generation models as world simulators. https:\/\/openai.com\/index\/sora\/ . Accessed: 2025-04-08."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"e_1_3_2_1_8_1","volume-title":"Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=oRLwyayrh1","author":"Chen Baoying","year":"2024","unstructured":"Baoying Chen, Jishen Zeng, Jianquan Yang, and Rui Yang. 2024b. DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images. In Forty-first International Conference on Machine Learning. https:\/\/openreview.net\/forum?id=oRLwyayrh1"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00347"},{"key":"e_1_3_2_1_10_1","unstructured":"Haoxing Chen Yan Hong Zizheng Huang Zhuoer Xu Zhangxuan Gu Yaohui Li Jun Lan Huijia Zhu Jianfu Zhang Weiqiang Wang and Huaxiong Li. 2024a. DeMamba: AI-Generated Video Detection on Million-Scale GenVideo Benchmark. arXiv Preprint 2405.19707. arXiv:2405.19707 https:\/\/arxiv.org\/abs\/2405.19707"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10095167"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3369711"},{"key":"e_1_3_2_1_16_1","volume-title":"V34","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, V34 (2021), 8780-8794."},{"key":"e_1_3_2_1_17_1","unstructured":"Google and Jigsaw. 2019. Contributing Data to Deepfake Detection Research. https:\/\/research.google\/blog\/contributing-data-to-deepfake-detection-research\/ . Accessed: 2025-04-10."},{"key":"e_1_3_2_1_18_1","unstructured":"Devin Gordon. 2024. What if A.I. Is Actually Good for Hollywood? https:\/\/www.nytimes.com\/2024\/11\/01\/magazine\/ai-hollywood-movies-cgi.html. Accessed: 2024-12-16."},{"key":"e_1_3_2_1_19_1","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 Preprint 2205.15868. arXiv:2205.15868 https:\/\/arxiv.org\/abs\/2205.15868"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Christian Intern\u00f2 Robert Geirhos Markus Olhofer Sunny Liu Barbara Hammer and David Klindt. 2026. AI-Generated Video Detection via Perceptual Straightening. arXiv:2507.00583 [cs.CV] https:\/\/arxiv.org\/abs\/2507.00583","DOI":"10.52202\/085713-0697"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3711896.3737399"},{"key":"e_1_3_2_1_22_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_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"e_1_3_2_1_25_1","volume-title":"Videopoet: A large language model for zero-shot video generation. arXiv preprint 2312.14125.","author":"Kondratyuk Dan","year":"2023","unstructured":"Dan Kondratyuk, Lijun Yu, Xiuye Gu, Jos\u00e9 Lezama, Jonathan Huang, Grant Schindler, Rachel Hornung, Vighnesh Birodkar, Jimmy Yan, Ming-Chang Chiu, et al., 2023. Videopoet: A large language model for zero-shot video generation. arXiv preprint 2312.14125. (2023)."},{"key":"e_1_3_2_1_26_1","volume-title":"Springer European Conference on Computer Vision (ECCV).","author":"Koutlis Christos","year":"2024","unstructured":"Christos Koutlis and Symeon Papadopoulos. 2024. Leveraging Representations from Intermediate Encoder-Blocks for Synthetic Image Detection. In Springer European Conference on Computer Vision (ECCV)."},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00432"},{"key":"e_1_3_2_1_28_1","volume-title":"Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Li Yuezun","year":"2020","unstructured":"Yuezun Li, Xin Yang, Pu Sun, Honggang Qi, and Siwei Lyu. 2020. Celeb-DF: A Large-scale Challenging Dataset for DeepFake Forensics. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_6"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.425"},{"key":"e_1_3_2_1_32_1","volume-title":"LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Nguyen Dat","year":"2024","unstructured":"Dat Nguyen, Nesryne Mejri, Inder Pal Singh, Polina Kuleshova, Marcella Astrid, Anis Kacem, Enjie Ghorbel, and Djamila Aouada. 2024. LAA-Net: Localized Artifact Attention Network for Quality-Agnostic and Generalizable Deepfake Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_33_1","unstructured":"Zhenliang Ni Qiangyu Yan Mouxiao Huang Tianning Yuan Yehui Tang Hailin Hu Xinghao Chen and Yunhe Wang. 2025. GenVidBench: A Challenging Benchmark for Detecting AI-Generated Video. arXiv Preprint 2501.11340. arXiv:2501.11340 https:\/\/arxiv.org\/abs\/2501.11340"},{"key":"e_1_3_2_1_34_1","volume-title":"Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741","author":"Nichol Alex","year":"2021","unstructured":"Alex Nichol, Prafulla Dhariwal, Aditya Ramesh, Pranav Shyam, Pamela Mishkin, Bob McGrew, Ilya Sutskever, and Mark Chen. 2021. Glide: Towards photorealistic image generation and editing with text-guided diffusion models. arXiv preprint arXiv:2112.10741 (2021)."},{"key":"e_1_3_2_1_35_1","unstructured":"Superior Court of the State of Washington for King County. 2024. FINDINGS OF FACT AND CONCLUSIONS OF LAW RE: FRYE HEARING ON ADMISSIBILITY OF VIDEOS ENHANCED BY ARTIFICIAL INTELLIGENCE. https:\/\/fingfx.thomsonreuters.com\/gfx\/legaldocs\/zgvokxekavd\/04192024ai_wash.pdf. Accessed: 2025-08-27."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"e_1_3_2_1_37_1","unstructured":"Yan Pang Yang Zhang and Tianhao Wang. 2024. VGMShield: Mitigating Misuse of Video Generative Models. arXiv Preprint 2402.13126. arXiv:2402.13126 https:\/\/arxiv.org\/abs\/2402.13126"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_2_1_40_1","volume-title":"International conference on machine learning. Pmlr, 8821-8831","author":"Ramesh Aditya","year":"2021","unstructured":"Aditya Ramesh, Mikhail Pavlov, Gabriel Goh, Scott Gray, Chelsea Voss, Alec Radford, Mark Chen, and Ilya Sutskever. 2021. Zero-shot text-to-image generation. In International conference on machine learning. Pmlr, 8821-8831."},{"key":"e_1_3_2_1_41_1","unstructured":"Runway Research. 2023. Gen-2: Generate novel videos with text images or video clips. https:\/\/runwayml.com\/research\/gen-2. Accessed: 2025-04-08."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_43_1","unstructured":"Kevin Roose. 2018. Here Come the Fake Videos Too. https:\/\/www.nytimes.com\/2018\/03\/04\/technology\/fake-videos-deepfakes.html. Accessed: 2025-08-27."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Olga Russakovsky Jia Deng Hao Su Jonathan Krause Sanjeev Satheesh Sean Ma Zhiheng Huang Andrej Karpathy Aditya Khosla Michael Bernstein et al. 2015. Imagenet large scale visual recognition challenge. International journal of computer vision V115 3 (2015) 211-252.","DOI":"10.1007\/s11263-015-0816-y"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_1_46_1","volume-title":"Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114","author":"Schuhmann Christoph","year":"2021","unstructured":"Christoph Schuhmann, Richard Vencu, Romain Beaumont, Robert Kaczmarczyk, Clayton Mullis, Aarush Katta, Theo Coombes, Jenia Jitsev, and Aran Komatsuzaki. 2021. Laion-400m: Open dataset of clip-filtered 400 million image-text pairs. arXiv preprint arXiv:2111.02114 (2021)."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3576915.3616588"},{"key":"e_1_3_2_1_48_1","volume-title":"On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection. In Conference on Neural Information Processing Systems (NeurIPS).","author":"Song Xiufeng","year":"2024","unstructured":"Xiufeng Song, Xiao Guo, Jiache Zhang, Qirui Li, Lei Bai, Xiaoming Liu, Guangtao Zhai, and Xiaohong Liu. 2024. On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection. In Conference on Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_49_1","volume-title":"Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection. In 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 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_50_1","volume-title":"Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Tan Chuangchuang","year":"2023","unstructured":"Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, and Yunchao Wei. 2023. Learning on Gradients: Generalized Artifacts Representation for GAN-Generated Images Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_1_52_1","unstructured":"Jiuniu Wang Hangjie Yuan Dayou Chen Yingya Zhang Xiang Wang and Shiwei Zhang. 2023c. Modelscope text-to-video technical report. arXiv Preprint 2308.06571. arXiv:2308.06571 https:\/\/arxiv.org\/abs\/2308.06571"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"e_1_3_2_1_54_1","volume-title":"DIRE for Diffusion-Generated Image Detection. In IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Wang Zhendong","year":"2023","unstructured":"Zhendong Wang, Jianmin Bao, Wengang Zhou, Weilun Wang, Hezhen Hu, Hong Chen, and Houqiang Li. 2023b. DIRE for Diffusion-Generated Image Detection. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_55_1","volume-title":"AltFreezing for More General Video Face Forgery Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR).","author":"Wang Zhendong","year":"2023","unstructured":"Zhendong Wang, Jianmin Bao, Wengang Zhou, Weilun Wang, and Houqiang Li. 2023a. AltFreezing for More General Video Face Forgery Detection. In IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_56_1","unstructured":"Zhiqiang Xia Zhaokang Chen Bin Wu Chao Li Kwok-Wai Hung Chao Zhan Yingjie He and Wenjiang Zhou. 2024. MuseV: Infinite-length and High Fidelity Virtual Human Video Generation with Visual Conditioned Parallel Denoising. https:\/\/tmelyralab.github.io\/MuseV_Page\/ . Accessed: 2025-04-13."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.571"},{"key":"e_1_3_2_1_58_1","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0201"},{"key":"e_1_3_2_1_59_1","volume-title":"Vript: A video is worth thousands of words. Advances in Neural Information Processing Systems, V37","author":"Yang Dongjie","year":"2024","unstructured":"Dongjie Yang, Suyuan Huang, Chengqiang Lu, Xiaodong Han, Haoxin Zhang, Yan Gao, Yao Hu, and Hai Zhao. 2024. Vript: A video is worth thousands of words. Advances in Neural Information Processing Systems, V37 (2024), 57240-57261."},{"key":"e_1_3_2_1_60_1","volume-title":"Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu, Ari Seff, Yinda Zhang, Shuran Song, Thomas Funkhouser, and Jianxiong Xiao. 2015. Lsun: Construction of a large-scale image dataset using deep learning with humans in the loop. arXiv preprint arXiv:1506.03365 (2015)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01194"},{"key":"e_1_3_2_1_62_1","volume-title":"Exploring Temporal Coherence for More General Video Face Forgery Detection. In IEEE\/CVF International Conference on Computer Vision (ICCV).","author":"Zheng Yinglin","year":"2021","unstructured":"Yinglin Zheng, Jianmin Bao, Dong Chen, Ming Zeng, and Fang Wen. 2021. Exploring Temporal Coherence for More General Video Face Forgery Detection. In IEEE\/CVF International Conference on Computer Vision (ICCV)."},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_23"}],"event":{"name":"KDD '26: The 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining","location":"Jeju Island Republic of Korea","sponsor":["SIGMOD ACM Special Interest Group on Management of Data","SIGKDD ACM Special Interest Group on Knowledge Discovery in Data"]},"container-title":["Proceedings of the 32nd ACM SIGKDD Conference on Knowledge Discovery and Data Mining V.2"],"original-title":[],"deposited":{"date-parts":[[2026,8,7]],"date-time":"2026-08-07T01:13:32Z","timestamp":1786065212000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3770855.3817509"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,8]]},"references-count":64,"alternative-id":["10.1145\/3770855.3817509","10.1145\/3770855"],"URL":"https:\/\/doi.org\/10.1145\/3770855.3817509","relation":{},"subject":[],"published":{"date-parts":[[2026,8,8]]},"assertion":[{"value":"2026-08-08","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}