{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T17:22:36Z","timestamp":1776100956468,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681445","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"3538-3547","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":6,"title":["Rethinking Image Editing Detection in the Era of Generative AI Revolution"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0000-4018-6194","authenticated-orcid":false,"given":"Zhihao","family":"Sun","sequence":"first","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-1192-7714","authenticated-orcid":false,"given":"Haipeng","family":"Fang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7857-1546","authenticated-orcid":false,"given":"Juan","family":"Cao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5342-1472","authenticated-orcid":false,"given":"Xinying","family":"Zhao","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences & University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3603-9743","authenticated-orcid":false,"given":"Danding","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.150"},{"key":"e_1_3_2_1_2_1","volume-title":"CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images. arXiv preprint arXiv:2303.14126","author":"Bird Jordan J","year":"2023","unstructured":"Jordan J Bird and Ahmad Lotfi. 2023. CIFAKE: Image Classification and Explainable Identification of AI-Generated Synthetic Images. arXiv preprint arXiv:2303.14126 (2023)."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19781-9_9"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01392"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ChinaSIP.2013.6625374"},{"key":"e_1_3_2_1_6_1","volume-title":"International conference on machine learning. PMLR, 3247--3258","author":"Frank Joel","year":"2020","unstructured":"Joel Frank, Thorsten Eisenhofer, Lea Sch\u00f6nherr, Asja Fischer, Dorothea Kolossa, and Thorsten Holz. 2020. Leveraging frequency analysis for deep fake image recognition. In International conference on machine learning. PMLR, 3247--3258."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW.2019.00018"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01974"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_19"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00096"},{"key":"e_1_3_2_1_12_1","volume-title":"International conference on machine learning. PMLR, 2668--2677","author":"Been","unstructured":"Been Kim et al. 2018. Interpretability beyond feature attribution: Quantitative testing with concept activation vectors (tcav). In International conference on machine learning. PMLR, 2668--2677."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"crossref","unstructured":"Alexander Kirillov Eric Mintun Nikhila Ravi Hanzi Mao Chloe Rolland Laura Gustafson Tete Xiao Spencer Whitehead Alexander C Berg Wan-Yen Lo et al. 2023. Segment anything. arXiv preprint arXiv:2304.02643 (2023).","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"e_1_3_2_1_14_1","volume-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597","author":"Li Junnan","year":"2023","unstructured":"Junnan Li, Dongxu Li, Silvio Savarese, and Steven Hoi. 2023. Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models. arXiv preprint arXiv:2301.12597 (2023)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"e_1_3_2_1_17_1","volume-title":"Visual news: Benchmark and challenges in news image captioning. arXiv preprint arXiv:2010.03743","author":"Liu Fuxiao","year":"2020","unstructured":"Fuxiao Liu, Yinghan Wang, Tianlu Wang, and Vicente Ordonez. 2020. Visual news: Benchmark and challenges in news image captioning. arXiv preprint arXiv:2010.03743 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3189545"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00808"},{"key":"e_1_3_2_1_21_1","volume-title":"Seeing is not always believing: A Quantitative Study on Human Perception of AI-Generated Images. arXiv preprint arXiv:2304.13023","author":"Lu Zeyu","year":"2023","unstructured":"Zeyu Lu, Di Huang, Lei Bai, Xihui Liu, Jingjing Qu, and Wanli Ouyang. 2023. Seeing is not always believing: A Quantitative Study on Human Perception of AI-Generated Images. arXiv preprint arXiv:2304.13023 (2023)."},{"key":"e_1_3_2_1_22_1","volume-title":"Jean Luc Dugelay, and PIC Marc","author":"Mahfoudi Ga\u00ebl","year":"2019","unstructured":"Ga\u00ebl Mahfoudi, Badr Tajini, Florent Retraint, Frederic Morain-Nicolier, Jean Luc Dugelay, and PIC Marc. 2019. DEFACTO: image and face manipulation dataset. In 2019 27Th european signal processing conference (EUSIPCO). IEEE, 1--5."},{"key":"e_1_3_2_1_23_1","volume-title":"IMD2020: a large-scale annotated dataset tailored for detecting manipulated images. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops. 71--80","author":"Novozamsky Adam","year":"2020","unstructured":"Adam Novozamsky, Babak Mahdian, and Stanislav Saic. 2020. IMD2020: a large-scale annotated dataset tailored for detecting manipulated images. In Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision Workshops. 71--80."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"e_1_3_2_1_25_1","first-page":"27730","article-title":"Training language models to follow instructions with human feedback","volume":"35","author":"Ouyang Long","year":"2022","unstructured":"Long Ouyang, Jeffrey Wu, Xu Jiang, Diogo Almeida, Carroll Wainwright, Pamela Mishkin, Chong Zhang, Sandhini Agarwal, Katarina Slama, Alex Ray, et al. 2022. Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, Vol. 35 (2022), 27730--27744.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_26_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_1_27_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_2_1_28_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_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_30_1","first-page":"36479","article-title":"Photorealistic text-to-image diffusion models with deep language understanding","volume":"35","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L Denton, Kamyar Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, et al. 2022. Photorealistic text-to-image diffusion models with deep language understanding. Advances in Neural Information Processing Systems, Vol. 35 (2022), 36479--36494.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/34.868688"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02049"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00323"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.149"},{"key":"e_1_3_2_1_35_1","volume-title":"International conference on machine learning. PMLR, 10347--10357","author":"Touvron Hugo","year":"2021","unstructured":"Hugo Touvron, Matthieu Cord, Matthijs Douze, Francisco Massa, Alexandre Sablayrolles, and Herv\u00e9 J\u00e9gou. 2021. Training data-efficient image transformers & distillation through attention. In International conference on machine learning. PMLR, 10347--10357."},{"key":"e_1_3_2_1_36_1","unstructured":"Luisa Verdoliva Davide Cozzolino and Koki Nagano. [n. d.]. 2022 IEEE Image and Video Processing Cup Synthetic Image Detection. ( [n. d.])."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"e_1_3_2_1_38_1","volume-title":"Benchmarking Deepart Detection. arXiv preprint arXiv:2302.14475","author":"Wang Yabin","year":"2023","unstructured":"Yabin Wang, Zhiwu Huang, and Xiaopeng Hong. 2023. Benchmarking Deepart Detection. arXiv preprint arXiv:2302.14475 (2023)."},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2016.7532339"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00977"},{"key":"e_1_3_2_1_41_1","volume-title":"Exposing fake images generated by text-to-image diffusion models. Pattern Recognition Letters","author":"Xu Qiang","year":"2023","unstructured":"Qiang Xu, Hao Wang, Laijin Meng, Zhongjie Mi, Jianye Yuan, and Hong Yan. 2023. Exposing fake images generated by text-to-image diffusion models. Pattern Recognition Letters (2023)."},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01763"},{"key":"e_1_3_2_1_43_1","volume-title":"Fingerprints of Generative Models in the Frequency Domain. arXiv preprint arXiv:2307.15977","author":"Yang Tianyun","year":"2023","unstructured":"Tianyun Yang, Juan Cao, Danding Wang, and Chang Xu. 2023. Fingerprints of Generative Models in the Frequency Domain. arXiv preprint arXiv:2307.15977 (2023)."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20391"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01522"},{"key":"e_1_3_2_1_46_1","volume-title":"Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al.","author":"Yu Jiahui","year":"2022","unstructured":"Jiahui Yu, Yuanzhong Xu, Jing Yu Koh, Thang Luong, Gunjan Baid, Zirui Wang, Vijay Vasudevan, Alexander Ku, Yinfei Yang, Burcu Karagol Ayan, et al. 2022. Scaling autoregressive models for content-rich text-to-image generation. arXiv preprint arXiv:2206.10789, Vol. 2, 3 (2022), 5."},{"key":"e_1_3_2_1_47_1","volume-title":"Ernie-vilg: Unified generative pre-training for bidirectional vision-language generation. arXiv preprint arXiv:2112.15283","author":"Zhang Han","year":"2021","unstructured":"Han Zhang, Weichong Yin, Yewei Fang, Lanxin Li, Boqiang Duan, Zhihua Wu, Yu Sun, Hao Tian, Hua Wu, and Haifeng Wang. 2021. Ernie-vilg: Unified generative pre-training for bidirectional vision-language generation. arXiv preprint arXiv:2112.15283 (2021)."},{"key":"e_1_3_2_1_48_1","volume-title":"Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543","author":"Zhang Lvmin","year":"2023","unstructured":"Lvmin Zhang and Maneesh Agrawala. 2023. Adding conditional control to text-to-image diffusion models. arXiv preprint arXiv:2302.05543 (2023)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00388"},{"key":"e_1_3_2_1_50_1","volume-title":"GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image. arXiv preprint arXiv:2306.08571","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. 2023. GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image. arXiv preprint arXiv:2306.08571 (2023)."}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681445","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681445","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T00:57:47Z","timestamp":1750294667000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681445"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":50,"alternative-id":["10.1145\/3664647.3681445","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681445","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}