{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,23]],"date-time":"2025-12-23T00:30:03Z","timestamp":1766449803958,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":31,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,8,25]]},"DOI":"10.1145\/3709022.3736547","type":"proceedings-article","created":{"date-parts":[[2025,7,3]],"date-time":"2025-07-03T09:05:26Z","timestamp":1751533526000},"page":"38-43","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Same Same, But Different?: Detecting AI-Generated Videos Using Knowledge Transfer"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-6567-8814","authenticated-orcid":false,"given":"Yuxi","family":"Jiang","sequence":"first","affiliation":[{"name":"Technische Universit\u00e4t Darmstadt, Darmstadt, Hesse, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-7398-0417","authenticated-orcid":false,"given":"Raphael Antonius","family":"Frick","sequence":"additional","affiliation":[{"name":"Fraunhofer SIT \/ ATHENE, Darmstadt, Hesse, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,8,25]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the European Conference on Computer Vision.","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 Proceedings of the European Conference on Computer Vision."},{"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:2311.15127 [cs.CV] https:\/\/arxiv.org\/abs\/2311.15127"},{"key":"e_1_3_2_1_3_1","unstructured":"Brian Dolhansky Joanna Bitton Ben Pflaum Jikuo Lu Russ Howes Menglin Wang and Cristian Canton Ferrer. 2020. The DeepFake Detection Challenge (DFDC) Dataset. arXiv:2006.07397 [cs.CV] https:\/\/arxiv.org\/abs\/2006.07397"},{"key":"e_1_3_2_1_4_1","unstructured":"Ian J. Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative Adversarial Networks. arXiv:1406.2661 [stat.ML]"},{"key":"e_1_3_2_1_5_1","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:2104.02617 [cs.CV] https:\/\/arxiv.org\/abs\/2104.02617","DOI":"10.1109\/ICME51207.2021.9428429"},{"key":"e_1_3_2_1_6_1","unstructured":"Yuwei Guo Ceyuan Yang Anyi Rao Zhengyang Liang Yaohui Wang Yu Qiao Maneesh Agrawala Dahua Lin and Bo Dai. 2024. AnimateDiff: Animate Your Personalized Text-to-Image Diffusion Models without Specific Tuning. arXiv:2307.04725 [cs.CV] https:\/\/arxiv.org\/abs\/2307.04725"},{"key":"e_1_3_2_1_7_1","unstructured":"Yue-Hua Han Tai-Ming Huang Kai-Lung Hua and Jun-Cheng Chen. 2025. Towards More General Video-based Deepfake Detection through Facial Component Guided Adaptation for Foundation Model. arXiv:2404.05583 [cs.CV] https:\/\/arxiv.org\/abs\/2404.05583"},{"key":"e_1_3_2_1_8_1","unstructured":"Kaiming He Xiangyu Zhang Shaoqing Ren and Jian Sun. 2015. Deep Residual Learning for Image Recognition. arXiv:1512.03385 [cs.CV] https:\/\/arxiv.org\/abs\/1512.03385"},{"key":"e_1_3_2_1_9_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. arXiv:2006.11239 [cs.LG] https:\/\/arxiv.org\/abs\/2006.11239"},{"key":"e_1_3_2_1_10_1","volume-title":"Long short-term memory. Neural computation 9, 8","author":"Hochreiter Sepp","year":"1997","unstructured":"Sepp Hochreiter and J\u00fcrgen Schmidhuber. 1997. Long short-term memory. Neural computation 9, 8 (1997), 1735--1780."},{"key":"e_1_3_2_1_11_1","volume-title":"Recap: Detecting Deepfake Video with Unpredictable Tampered Traces via Recovering Faces and Mapping Recovered Faces. arXiv:2308.09921 [cs.CV] https:\/\/arxiv.org\/abs\/2308.09921","author":"Hu Juan","year":"2023","unstructured":"Juan Hu, Xin Liao, Difei Gao, Satoshi Tsutsui, Qian Wang, Zheng Qin, and Mike Zheng Shou. 2023. Recap: Detecting Deepfake Video with Unpredictable Tampered Traces via Recovering Faces and Mapping Recovered Faces. arXiv:2308.09921 [cs.CV] https:\/\/arxiv.org\/abs\/2308.09921"},{"key":"e_1_3_2_1_12_1","volume-title":"Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces. arXiv:2401.13516 [cs.CV] https:\/\/arxiv.org\/abs\/2401.13516","author":"Hu Juan","year":"2024","unstructured":"Juan Hu, Xin Liao, Difei Gao, Satoshi Tsutsui, Qian Wang, Zheng Qin, and Mike Zheng Shou. 2024. Delocate: Detection and Localization for Deepfake Videos with Randomly-Located Tampered Traces. arXiv:2401.13516 [cs.CV] https:\/\/arxiv.org\/abs\/2401.13516"},{"key":"e_1_3_2_1_13_1","unstructured":"International Telecommunication Union (ITU). 2023. Mobile Phone Ownership. https:\/\/www.itu.int\/itu-d\/reports\/statistics\/2023\/10\/10\/ff23-mobile-phone-ownership\/"},{"key":"e_1_3_2_1_14_1","unstructured":"Yonghyun Jeong Doyeon Kim Seungjai Min Seongho Joe Youngjune Gwon and Jongwon Choi. 2021. BiHPF: Bilateral High-Pass Filters for Robust Deepfake Detection. arXiv:2109.00911 [cs.CV] https:\/\/arxiv.org\/abs\/2109.00911"},{"key":"e_1_3_2_1_15_1","volume-title":"DiffWave: A Versatile Diffusion Model for Audio Synthesis. ArXiv abs\/2009.09761","author":"Kong Zhifeng","year":"2020","unstructured":"Zhifeng Kong, Wei Ping, Jiaji Huang, Kexin Zhao, and Bryan Catanzaro. 2020. DiffWave: A Versatile Diffusion Model for Audio Synthesis. ArXiv abs\/2009.09761 (2020). https:\/\/api.semanticscholar.org\/CorpusID:221818900"},{"key":"e_1_3_2_1_16_1","unstructured":"Haotian Liu Chunyuan Li Qingyang Wu and Yong Jae Lee. 2023. Visual Instruction Tuning. arXiv:2304.08485 [cs.CV] https:\/\/arxiv.org\/abs\/2304.08485"},{"key":"e_1_3_2_1_17_1","unstructured":"Ruipeng Ma Jinhao Duan Fei Kong Xiaoshuang Shi and Kaidi Xu. 2023. Exposing the Fake: Effective Diffusion-Generated Images Detection. arXiv:2307.06272 [cs.CV] https:\/\/arxiv.org\/abs\/2307.06272"},{"key":"e_1_3_2_1_18_1","unstructured":"Jean Mackenzie and Leehyun Choi. [n.d.]. Inside the deepfake porn crisis engulfing Korean schools. https:\/\/www.bbc.com\/news\/articles\/cpdlpj9zn9go."},{"key":"e_1_3_2_1_19_1","unstructured":"Midjourney. [n.d.]. Midjourney AI Generator. https:\/\/www.midjourney.com."},{"key":"e_1_3_2_1_20_1","volume-title":"Dream-Fusion: Text-to-3D using 2D Diffusion. ArXiv abs\/2209.14988","author":"Poole Ben","year":"2022","unstructured":"Ben Poole, Ajay Jain, Jonathan T. Barron, and Ben Mildenhall. 2022. Dream-Fusion: Text-to-3D using 2D Diffusion. ArXiv abs\/2209.14988 (2022). https:\/\/api.semanticscholar.org\/CorpusID:252596091"},{"key":"e_1_3_2_1_21_1","volume-title":"Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, Gretchen Krueger, and Ilya Sutskever.","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, Gretchen Krueger, and Ilya Sutskever. 2021. Learning Transferable Visual Models From Natural Language Supervision. arXiv:2103.00020 [cs.CV] https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"crossref","unstructured":"Robin Rombach Andreas Blattmann Dominik Lorenz Patrick Esser and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. arXiv:2112.10752 [cs.CV] https:\/\/arxiv.org\/abs\/2112.10752","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/78.650093"},{"key":"e_1_3_2_1_24_1","unstructured":"Karen Simonyan and Andrew Zisserman. 2015. Very Deep Convolutional Networks for Large-Scale Image Recognition. arXiv:1409.1556 [cs.CV] https:\/\/arxiv.org\/abs\/1409.1556"},{"key":"e_1_3_2_1_25_1","unstructured":"Xiufeng Song Xiao Guo Jiache Zhang Qirui Li Lei Bai Xiaoming Liu Guangtao Zhai and Xiaohong Liu. 2025. On Learning Multi-Modal Forgery Representation for Diffusion Generated Video Detection. arXiv:2410.23623 [cs.CV] https:\/\/arxiv.org\/abs\/2410.23623"},{"key":"e_1_3_2_1_26_1","volume-title":"Amir Roshan Zamir, and Mubarak Shah","author":"Soomro Khurram","year":"2012","unstructured":"Khurram Soomro, Amir Roshan Zamir, and Mubarak Shah. 2012. UCF101: A Dataset of 101 Human Actions Classes From Videos in The Wild. arXiv:1212.0402 [cs.CV] https:\/\/arxiv.org\/abs\/1212.0402"},{"key":"e_1_3_2_1_27_1","unstructured":"Stability AI. 2023. Stable Video Diffusion Now Available on Stability AI Developer Platform API. https:\/\/stability.ai\/news\/introducing-stable-video-diffusion-api."},{"key":"e_1_3_2_1_28_1","volume-title":"Le","author":"Tan Mingxing","year":"2020","unstructured":"Mingxing Tan and Quoc V. Le. 2020. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. arXiv:1905.11946 [cs.LG] https:\/\/arxiv.org\/abs\/1905.11946"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"crossref","unstructured":"Zhendong Wang Jianmin Bao Wengang Zhou Weilun Wang Hezhen Hu Hong Chen and Houqiang Li. 2023. DIRE for Diffusion-Generated Image Detection. arXiv:2303.09295 [cs.CV] https:\/\/arxiv.org\/abs\/2303.09295","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"e_1_3_2_1_30_1","volume-title":"Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou.","author":"Zhang David Junhao","year":"2023","unstructured":"David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou. 2023. Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation. arXiv preprint arXiv:2309.15818 (2023)."},{"key":"e_1_3_2_1_31_1","volume-title":"Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou.","author":"Zhang David Junhao","year":"2023","unstructured":"David Junhao Zhang, Jay Zhangjie Wu, Jia-Wei Liu, Rui Zhao, Lingmin Ran, Yuchao Gu, Difei Gao, and Mike Zheng Shou. 2023. Show-1: Marrying Pixel and Latent Diffusion Models for Text-to-Video Generation. arXiv:2309.15818 [cs.CV] https:\/\/arxiv.org\/abs\/2309.15818"}],"event":{"name":"ASIA CCS '25: ACM Asia Conference on Computer and Communications Security","sponsor":["SIGSAC ACM Special Interest Group on Security, Audit, and Control"],"location":"Hanoi Vietnam","acronym":"ASIA CCS '25"},"container-title":["Proceedings of the 4th Workshop on Security Implications of Deepfakes and Cheapfakes"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3709022.3736547","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,3]],"date-time":"2025-09-03T14:19:08Z","timestamp":1756909148000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3709022.3736547"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,25]]},"references-count":31,"alternative-id":["10.1145\/3709022.3736547","10.1145\/3709022"],"URL":"https:\/\/doi.org\/10.1145\/3709022.3736547","relation":{},"subject":[],"published":{"date-parts":[[2025,8,25]]},"assertion":[{"value":"2025-08-25","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}