{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:13:40Z","timestamp":1765008820015,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":48,"publisher":"ACM","funder":[{"DOI":"10.13039\/501100004423","name":"Waseda University","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100004423","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,12,9]]},"DOI":"10.1145\/3743093.3770967","type":"proceedings-article","created":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:06:16Z","timestamp":1765008376000},"page":"1-8","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Time Step Generating: A Universal Synthesized Deepfake Image Detector"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0006-8906-3770","authenticated-orcid":false,"given":"Ziyue","family":"Zeng","sequence":"first","affiliation":[{"name":"\u5927\u5b66\u9662\u57fa\u5e79\u7406\u5de5\u5b66\u90e8\u7814\u7a76\u79d1\u3000\u60c5\u5831\u7406\u5de5\u30fb\u60c5\u5831\u901a\u4fe1\u5c02\u653b, Waseda University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7358-6315","authenticated-orcid":false,"given":"Yupei","family":"Guo","sequence":"additional","affiliation":[{"name":"Tokyo University of Science, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-0906-6901","authenticated-orcid":false,"given":"Haoyuan","family":"Liu","sequence":"additional","affiliation":[{"name":"\u5927\u5b66\u9662\u57fa\u5e79\u7406\u5de5\u5b66\u90e8\u7814\u7a76\u79d1\u3000\u60c5\u5831\u7406\u5de5\u30fb\u60c5\u5831\u901a\u4fe1\u5c02\u653b, Waseda University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0854-0393","authenticated-orcid":false,"given":"Dingjie","family":"Peng","sequence":"additional","affiliation":[{"name":"\u5927\u5b66\u9662\u57fa\u5e79\u7406\u5de5\u5b66\u90e8\u7814\u7a76\u79d1\u3000\u60c5\u5831\u7406\u5de5\u30fb\u60c5\u5831\u901a\u4fe1\u5c02\u653b, Waseda University, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9306-688X","authenticated-orcid":false,"given":"Hiroshi","family":"Watanabe","sequence":"additional","affiliation":[{"name":"\u5927\u5b66\u9662\u57fa\u5e79\u7406\u5de5\u5b66\u90e8\u7814\u7a76\u79d1\u3000\u60c5\u5831\u7406\u5de5\u30fb\u60c5\u5831\u901a\u4fe1\u5c02\u653b, Waseda University, Tokyo, Japan"}]}],"member":"320","published-online":{"date-parts":[[2025,12,6]]},"reference":[{"key":"e_1_3_3_1_2_2","volume-title":"International Conference on Learning Representations","author":"Brock Andrew","year":"2019","unstructured":"Andrew Brock, Jeff Donahue, and Karen Simonyan. 2019. Large Scale GAN Training for High Fidelity Natural Image Synthesis. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=B1xsqj09Fm"},{"key":"e_1_3_3_1_3_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01764"},{"key":"e_1_3_3_1_4_2","unstructured":"Bar Cavia Eliahu Horwitz Tal Reiss and Yedid Hoshen. 2024. Real-Time Deepfake Detection in the Real-World. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2406.09398 (2024)."},{"key":"e_1_3_3_1_5_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58574-7_7"},{"key":"e_1_3_3_1_6_2","volume-title":"The Twelfth International Conference on Learning Representations","author":"Chen Junsong","year":"2024","unstructured":"Junsong Chen, Jincheng YU, Chongjian GE, Lewei Yao, Enze Xie, Zhongdao Wang, James Kwok, Ping Luo, Huchuan Lu, and Zhenguo Li. 2024. PixArt-$\\alpha$: Fast Training of Diffusion Transformer for Photorealistic Text-to-Image Synthesis. In The Twelfth International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=eAKmQPe3m1"},{"key":"e_1_3_3_1_7_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01197"},{"key":"e_1_3_3_1_8_2","first-page":"8780","volume-title":"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. In Advances in Neural Information Processing Systems , M.\u00a0Ranzato, A.\u00a0Beygelzimer, Y.\u00a0Dauphin, P.S. Liang, and J.\u00a0Wortman Vaughan (Eds.), Vol.\u00a034. Curran Associates, Inc., 8780\u20138794. https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2021\/file\/49ad23d1ec9fa4bd8d77d02681df5cfa-Paper.pdf"},{"key":"e_1_3_3_1_9_2","volume-title":"Advances in Neural Information Processing Systems","author":"Goodfellow Ian","year":"2014","unstructured":"Ian Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems , Z.\u00a0Ghahramani, M.\u00a0Welling, C.\u00a0Cortes, N.\u00a0Lawrence, and K.Q. Weinberger (Eds.), Vol.\u00a027. Curran Associates, Inc.https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2014\/file\/5ca3e9b122f61f8f06494c97b1afccf3-Paper.pdf"},{"key":"e_1_3_3_1_10_2","unstructured":"Patrick Grommelt Louis Weiss Franz-Josef Pfreundt and Janis Keuper. 2024. Fake or JPEG? Revealing Common Biases in Generated Image Detection Datasets. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2403.17608 (2024)."},{"key":"e_1_3_3_1_11_2","unstructured":"Jiaxi Gu Xiaojun Meng Guansong Lu Lu Hou Niu Minzhe Xiaodan Liang Lewei Yao Runhui Huang Wei Zhang Xin Jiang et\u00a0al. 2022. Wukong: A 100 million large-scale chinese cross-modal pre-training benchmark. Advances in Neural Information Processing Systems 35 (2022) 26418\u201326431."},{"key":"e_1_3_3_1_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_3_1_13_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_3_1_14_2","unstructured":"Zhiyuan He Pin-Yu Chen and Tsung-Yi Ho. 2024. RIGID: A Training-free and Model-Agnostic Framework for Robust AI-Generated Image Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2405.20112 (2024)."},{"key":"e_1_3_3_1_15_2","first-page":"332","volume-title":"IEEE Global Conference on Consumer Electronics (GCCE2024).","author":"Hiroshi\u00a0Watanabe Yurika\u00a0Fujinami","year":"2024","unstructured":"Yurika\u00a0Fujinami Hiroshi\u00a0Watanabe. 2024. Adversarial Level of Face Images Generated by Prompt-Based Image Coding in Face Recognition System. In IEEE Global Conference on Consumer Electronics (GCCE2024).332\u2013333."},{"key":"e_1_3_3_1_16_2","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems 33 (2020) 6840\u20136851."},{"key":"e_1_3_3_1_17_2","unstructured":"Jonathan Ho and Tim Salimans. 2022. Classifier-free diffusion guidance. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2207.12598 (2022)."},{"key":"e_1_3_3_1_18_2","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."},{"key":"e_1_3_3_1_19_2","doi-asserted-by":"crossref","unstructured":"Felix Juefei-Xu Run Wang Yihao Huang Qing Guo Lei Ma and Yang Liu. 2022. Countering malicious deepfakes: Survey battleground and horizon. International journal of computer vision 130 7 (2022) 1678\u20131734.","DOI":"10.1007\/s11263-022-01606-8"},{"key":"e_1_3_3_1_20_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00582"},{"key":"e_1_3_3_1_21_2","unstructured":"Diederik\u00a0P Kingma. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_1_22_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72667-5_8"},{"key":"e_1_3_3_1_23_2","unstructured":"Jiawei Liang Siyuan Liang Aishan Liu Xiaojun Jia Junhao Kuang and Xiaochun Cao. 2024. Poisoned forgery face: Towards backdoor attacks on face forgery detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2402.11473 (2024)."},{"key":"e_1_3_3_1_24_2","first-page":"17006","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Luo Yunpeng","year":"2024","unstructured":"Yunpeng Luo, Junlong Du, Ke Yan, and Shouhong Ding. 2024. LaRE\u23032: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 17006\u201317015."},{"key":"e_1_3_3_1_25_2","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:https:\/\/arXiv.org\/abs\/2112.10741 (2021)."},{"key":"e_1_3_3_1_26_2","first-page":"8162","volume-title":"International conference on machine learning","author":"Nichol Alexander\u00a0Quinn","year":"2021","unstructured":"Alexander\u00a0Quinn Nichol and Prafulla Dhariwal. 2021. Improved denoising diffusion probabilistic models. In International conference on machine learning. PMLR, 8162\u20138171."},{"key":"e_1_3_3_1_27_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"e_1_3_3_1_28_2","unstructured":"Bohao Peng Jian Wang Yuechen Zhang Wenbo Li Ming-Chang Yang and Jiaya Jia. 2024. Controlnext: Powerful and efficient control for image and video generation. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2408.06070 (2024)."},{"key":"e_1_3_3_1_29_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_3_1_30_2","unstructured":"Jonas Ricker Simon Damm Thorsten Holz and Asja Fischer. 2022. Towards the detection of diffusion model deepfakes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2210.14571 (2022)."},{"key":"e_1_3_3_1_31_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00872"},{"key":"e_1_3_3_1_32_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_3_1_33_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_3_1_34_2","first-page":"2256","volume-title":"International conference on machine learning","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\u20132265."},{"key":"e_1_3_3_1_35_2","volume-title":"International Conference on Learning Representations","author":"Song Jiaming","year":"2021","unstructured":"Jiaming Song, Chenlin Meng, and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=St1giarCHLP"},{"key":"e_1_3_3_1_36_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00020"},{"key":"e_1_3_3_1_37_2","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"e_1_3_3_1_38_2","unstructured":"Hansi Teng Hongyu Jia Lei Sun Lingzhi Li Maolin Li Mingqiu Tang Shuai Han Tianning Zhang WQ Zhang Weifeng Luo et\u00a0al. 2025. MAGI-1: Autoregressive Video Generation at Scale. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2505.13211 (2025)."},{"key":"e_1_3_3_1_39_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01522"},{"key":"e_1_3_3_1_40_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"e_1_3_3_1_41_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"e_1_3_3_1_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3643491.3660280"},{"key":"e_1_3_3_1_43_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00548"},{"key":"e_1_3_3_1_44_2","unstructured":"Zhipei Xu Xuanyu Zhang Runyi Li Zecheng Tang Qing Huang and Jian Zhang. 2024. Fakeshield: Explainable image forgery detection and localization via multi-modal large language models. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2410.02761 (2024)."},{"key":"e_1_3_3_1_45_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00787"},{"key":"e_1_3_3_1_46_2","unstructured":"Zhiyuan Yan Jiangming Wang Peng Jin Ke-Yue Zhang Chengchun Liu Shen Chen Taiping Yao Shouhong Ding Baoyuan Wu and Li Yuan. 2024. Orthogonal Subspace Decomposition for Generalizable AI-Generated Image Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/2411.15633 (2024)."},{"key":"e_1_3_3_1_47_2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00704"},{"key":"e_1_3_3_1_48_2","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859763"},{"key":"e_1_3_3_1_49_2","unstructured":"Mingjian Zhu Hanting Chen Qiangyu Yan Xudong Huang Guanyu Lin Wei Li Zhijun Tu Hailin Hu Jie Hu and Yunhe Wang. 2024. Genimage: A million-scale benchmark for detecting ai-generated image. Advances in Neural Information Processing Systems 36 (2024)."}],"event":{"name":"MMAsia '25: ACM Multimedia Asia","location":"Kuala Lumpur Malaysia","acronym":"MMAsia '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 7th ACM International Conference on Multimedia in Asia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3743093.3770967","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T08:08:52Z","timestamp":1765008532000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3743093.3770967"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,12,6]]},"references-count":48,"alternative-id":["10.1145\/3743093.3770967","10.1145\/3743093"],"URL":"https:\/\/doi.org\/10.1145\/3743093.3770967","relation":{},"subject":[],"published":{"date-parts":[[2025,12,6]]},"assertion":[{"value":"2025-12-06","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}