{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,9]],"date-time":"2026-05-09T16:40:43Z","timestamp":1778344843260,"version":"3.51.4"},"publisher-location":"New York, NY, USA","reference-count":82,"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:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Research Foundation, Singapore under its Strategic Capability Research Centres Funding Initiative"},{"name":"Shenzhen College Stability Support Plan","award":["Grant No. GXWD20220817144428005"],"award-info":[{"award-number":["Grant No. GXWD20220817144428005"]}]},{"name":"Key R\\&D Program of Shandong (Major scientific and technological innovation projects)","award":["No.:2020CXGC010111"],"award-info":[{"award-number":["No.:2020CXGC010111"]}]},{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["Grant No. 62236003; No.:U1936203"],"award-info":[{"award-number":["Grant No. 62236003; No.:U1936203"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3680797","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:49Z","timestamp":1729925989000},"page":"5939-5948","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":35,"title":["Diffusion Facial Forgery Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7436-0162","authenticated-orcid":false,"given":"Harry","family":"Cheng","sequence":"first","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8691-5372","authenticated-orcid":false,"given":"Yangyang","family":"Guo","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2920-6099","authenticated-orcid":false,"given":"Tianyi","family":"Wang","sequence":"additional","affiliation":[{"name":"Nanyang Technological University, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology (Shenzhen), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4846-2015","authenticated-orcid":false,"given":"Mohan","family":"Kankanhalli","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore, Singapore"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"crossref","unstructured":"Omri Avrahami Dani Lischinski and Ohad Fried. 2022. Blended Diffusion for Text-driven Editing of Natural Images. In CVPR. 18187--18197.","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"crossref","unstructured":"Yeqi Bai Tao Ma Lipo Wang and Zhenjie Zhang. 2022. Speech Fusion to Face: Bridging the Gap Between Human's Vocal Characteristics and Facial Imaging. In ACM MM. 2042--2050.","DOI":"10.1145\/3503161.3547850"},{"key":"e_1_3_2_1_3_1","unstructured":"Fan Bao Chongxuan Li Jun Zhu and Bo Zhang. 2022. Analytic-DPM: an Analytic Estimate of the Optimal Reverse Variance in Diffusion Probabilistic Models. In ICLR. 1--12."},{"key":"e_1_3_2_1_4_1","volume-title":"Willcocks","author":"Bond-Taylor Sam","year":"2022","unstructured":"Sam Bond-Taylor, Peter Hessey, Hiroshi Sasaki, Toby P. Breckon, and Chris G. Willcocks. 2022. Unleashing Transformers: Parallel Token Prediction with Discrete Absorbing Diffusion for Fast High-Resolution Image Generation from Vector-Quantized Codes. In ECCV. 170--188."},{"key":"e_1_3_2_1_5_1","volume-title":"Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2. CoRR","author":"Borji Ali","year":"2022","unstructured":"Ali Borji. 2022. Generated Faces in the Wild: Quantitative Comparison of Stable Diffusion, Midjourney and DALL-E 2. CoRR (2022), 1--4."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"crossref","unstructured":"Liang Chen Yong Zhang Yibing Song Lingqiao Liu and Jue Wang. 2022. Self-supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection. In CVPR. 18689--18698.","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"e_1_3_2_1_7_1","volume-title":"Cohen","author":"Chen Wenhu","year":"2023","unstructured":"Wenhu Chen, Hexiang Hu, Chitwan Saharia, and William W. Cohen. 2023. Re-Imagen: Retrieval-Augmented Text-to-Image Generator. In ICLR. 1--9."},{"key":"e_1_3_2_1_8_1","volume-title":"DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis. CoRR","author":"Chen Zhongxi","year":"2024","unstructured":"Zhongxi Chen, Ke Sun, Ziyin Zhou, Xianming Lin, Xiaoshuai Sun, Liujuan Cao, and Rongrong Ji. 2024. DiffusionFace: Towards a Comprehensive Dataset for Diffusion-Based Face Forgery Analysis. CoRR (2024), 1--10."},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3625231"},{"key":"e_1_3_2_1_10_1","volume-title":"Kankanhalli","author":"Cheng Harry","year":"2023","unstructured":"Harry Cheng, Yangyang Guo, Tianyi Wang, Liqiang Nie, and Mohan S. Kankanhalli. 2023. Towards Generalizable Deepfake Detection by Primary Region Regularization. CoRR (2023), 1--12."},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"crossref","unstructured":"Joon Son Chung Arsha Nagrani and Andrew Zisserman. 2018. VoxCeleb2: Deep Speaker Recognition. In Interspeech. 1086--1090.","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","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. 1--5.","DOI":"10.1109\/ICASSP49357.2023.10095167"},{"key":"e_1_3_2_1_13_1","volume-title":"Radu Tudor Ionescu, and Mubarak Shah","author":"Croitoru Florinel-Alin","year":"2023","unstructured":"Florinel-Alin Croitoru, Vlad Hondru, Radu Tudor Ionescu, and Mubarak Shah. 2023. Reverse Stable Diffusion: What prompt was used to generate this image? CoRR (2023), 1--13."},{"key":"e_1_3_2_1_14_1","unstructured":"Prafulla Dhariwal and Alexander Quinn Nichol. 2021. Diffusion Models Beat GANs on Image Synthesis. In NeurIPS. 8780--8794."},{"key":"e_1_3_2_1_15_1","volume-title":"The DeepFake Detection Challenge Dataset. CoRR","author":"Dolhansky Brian","year":"2020","unstructured":"Brian Dolhansky, Joanna Bitton, Ben Pflaum, Jikuo Lu, Russ Howes, Menglin Wang, and Cristian Canton-Ferrer. 2020. The DeepFake Detection Challenge Dataset. CoRR (2020), 1--13."},{"key":"e_1_3_2_1_16_1","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 ICML. 3247--3258."},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"crossref","unstructured":"Shuyang Gu Dong Chen Jianmin Bao Fang Wen Bo Zhang Dongdong Chen Lu Yuan and Baining Guo. 2022. Vector Quantized Diffusion Model for Text-to-Image Synthesis. In CVPR. 10686--10696.","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"crossref","unstructured":"Xiao Guo Xiaohong Liu Zhiyuan Ren Steven Grosz Iacopo Masi and Xiaoming Liu. 2023. Hierarchical Fine-Grained Image Forgery Detection and Localization. In CVPR. 3155--3165.","DOI":"10.1109\/CVPR52729.2023.00308"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"crossref","unstructured":"Alexandros Haliassos Rodrigo Mira Stavros Petridis and Maja Pantic. 2022. Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection. In CVPR. 14930--14942.","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"e_1_3_2_1_21_1","unstructured":"Yinan He Bei Gan Siyu Chen Yichun Zhou Guojun Yin Luchuan Song Lu Sheng Jing Shao and Ziwei Liu. 2021. ForgeryNet: A Versatile Benchmark for Comprehensive Forgery Analysis. In CVPR. 4360--4369."},{"key":"e_1_3_2_1_22_1","unstructured":"Jonathan Ho Ajay Jain and Pieter Abbeel. 2020. Denoising Diffusion Probabilistic Models. In NeurIPS. 1--12."},{"key":"e_1_3_2_1_23_1","volume-title":"JMLR","volume":"23","author":"Ho Jonathan","year":"2022","unstructured":"Jonathan Ho, Chitwan Saharia, William Chan, David J. Fleet, Mohammad Norouzi, and Tim Salimans. 2022. Cascaded Diffusion Models for High Fidelity Image Generation. JMLR, Vol. 23 (2022), 47:1--47:33."},{"key":"e_1_3_2_1_24_1","unstructured":"Edward J. Hu Yelong Shen Phillip Wallis Zeyuan Allen-Zhu Yuanzhi Li Shean Wang Lu Wang and Weizhu Chen. 2022. LoRA: Low-Rank Adaptation of Large Language Models. In ICLR. 1--13."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"crossref","unstructured":"Baojin Huang Zhongyuan Wang Jifan Yang Jiaxin Ai Qin Zou Qian Wang and Dengpan Ye. 2023. Implicit Identity Driven Deepfake Face Swapping Detection. In CVPR. 4490--4499.","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"crossref","unstructured":"Ziqi Huang Kelvin C. K. Chan Yuming Jiang and Ziwei Liu. 2023. Collaborative Diffusion for Multi-Modal Face Generation and Editing. In CVPR. 6080--6090.","DOI":"10.1109\/CVPR52729.2023.00589"},{"key":"e_1_3_2_1_27_1","volume-title":"Efros","author":"Huh Minyoung","year":"2018","unstructured":"Minyoung Huh, Andrew Liu, Andrew Owens, and Alexei A. Efros. 2018. Fighting Fake News: Image Splice Detection via Learned Self-Consistency. In ECCV. 106--124."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530104"},{"key":"e_1_3_2_1_29_1","volume-title":"Imagic: Text-Based Real Image Editing with Diffusion Models. In CVPR. 6007--6017.","author":"Kawar Bahjat","year":"2023","unstructured":"Bahjat Kawar, Shiran Zada, Oran Lang, Omer Tov, Huiwen Chang, Tali Dekel, Inbar Mosseri, and Michal Irani. 2023. Imagic: Text-Based Real Image Editing with Diffusion Models. In CVPR. 6007--6017."},{"key":"e_1_3_2_1_30_1","volume-title":"DiffFace: Diffusion-based Face Swapping with Facial Guidance. CoRR","author":"Kim Kihong","year":"2022","unstructured":"Kihong Kim, Yunho Kim, Seokju Cho, Junyoung Seo, Jisu Nam, Kychul Lee, Seungryong Kim, and KwangHee Lee. 2022. DiffFace: Diffusion-based Face Swapping with Facial Guidance. CoRR (2022), 1--11."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"crossref","unstructured":"Minchul Kim Feng Liu Anil K. Jain and Xiaoming Liu. 2023. DCFace: Synthetic Face Generation with Dual Condition Diffusion Model. In CVPR. 12715--12725.","DOI":"10.1109\/CVPR52729.2023.01223"},{"key":"e_1_3_2_1_32_1","volume-title":"BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis. In ICLR. 1--12.","author":"Lam Max W. Y.","year":"2022","unstructured":"Max W. Y. Lam, Jun Wang, Dan Su, and Dong Yu. 2022. BDDM: Bilateral Denoising Diffusion Models for Fast and High-Quality Speech Synthesis. In ICLR. 1--12."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"crossref","unstructured":"Cheng-Han Lee Ziwei Liu Lingyun Wu and Ping Luo. 2020. MaskGAN: Towards Diverse and Interactive Facial Image Manipulation. In CVPR. 5548--5557.","DOI":"10.1109\/CVPR42600.2020.00559"},{"key":"e_1_3_2_1_34_1","first-page":"3050","article-title":"Localization of Diffusion-Based Inpainting in Digital Images","volume":"12","author":"Li Haodong","year":"2017","unstructured":"Haodong Li, Weiqi Luo, and Jiwu Huang. 2017. Localization of Diffusion-Based Inpainting in Digital Images. IEEE TIFS, Vol. 12, 12 (2017), 3050--3064.","journal-title":"IEEE TIFS"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"crossref","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 CVPR. 5000--5009.","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"crossref","unstructured":"Yixuan Li Chao Ma Yichao Yan Wenhan Zhu and Xiaokang Yang. 2023. 3D-Aware Face Swapping. In CVPR. 12705--12714.","DOI":"10.1109\/CVPR52729.2023.01222"},{"key":"e_1_3_2_1_37_1","unstructured":"Luping Liu Yi Ren Zhijie Lin and Zhou Zhao. 2022. Pseudo Numerical Methods for Diffusion Models on Manifolds. In ICLR. 1--11."},{"key":"e_1_3_2_1_38_1","first-page":"541","article-title":"Two-Stage Copy-Move Forgery Detection With Self Deep Matching and Proposal SuperGlue","volume":"31","author":"Liu Yaqi","year":"2022","unstructured":"Yaqi Liu, Chao Xia, Xiaobin Zhu, and Shengwei Xu. 2022. Two-Stage Copy-Move Forgery Detection With Self Deep Matching and Proposal SuperGlue. IEEE TIP, Vol. 31 (2022), 541--555.","journal-title":"IEEE TIP"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"crossref","unstructured":"Andreas Lugmayr Martin Danelljan Andr\u00e9s Romero Fisher Yu Radu Timofte and Luc Van Gool. 2022. RePaint: Inpainting using Denoising Diffusion Probabilistic Models. In CVPR. 11451--11461.","DOI":"10.1109\/CVPR52688.2022.01117"},{"key":"e_1_3_2_1_40_1","volume-title":"Shenoy Pratik Gurudatt","author":"Masi Iacopo","year":"2020","unstructured":"Iacopo Masi, Aditya Killekar, Royston Marian Mascarenhas, Shenoy Pratik Gurudatt, and Wael AbdAlmageed. 2020. Two-Branch Recurrent Network for Isolating Deepfakes in Videos. In ECCV. 667--684."},{"key":"e_1_3_2_1_41_1","unstructured":"Midjourney. 2022. https:\/\/www.midjourney.com. https:\/\/www.midjourney.com\/"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"crossref","unstructured":"Shivansh Mundra Gonzalo J. Aniano Porcile Smit Marvaniya James R. Verbus and Hany Farid. 2023. Exposing GAN-Generated Profile Photos from Compact Embeddings. In CVPRW. 884--892.","DOI":"10.1109\/CVPRW59228.2023.00095"},{"key":"e_1_3_2_1_43_1","unstructured":"Alexander Quinn Nichol and Prafulla Dhariwal. 2021. Improved Denoising Diffusion Probabilistic Models. In ICML. 8162--8171."},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"crossref","unstructured":"Nikita Pavlichenko and Dmitry Ustalov. 2023. Best Prompts for Text-to-Image Models and How to Find Them. In SIGIR. 2067--2071.","DOI":"10.1145\/3539618.3592000"},{"key":"e_1_3_2_1_45_1","volume-title":"SDXL: Improving Latent Diffusion Models for High-Resolution Image Synthesis. CoRR","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. CoRR (2023), 1--21."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"crossref","unstructured":"Yuyang Qian Guojun Yin Lu Sheng Zixuan Chen and Jing Shao. 2020. Thinking in Frequency: Face Forgery Detection by Mining Frequency-Aware Clues. In ECCV. 86--103.","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"e_1_3_2_1_47_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. In ICML. 8748--8763."},{"key":"e_1_3_2_1_48_1","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 ICML. 8821--8831."},{"key":"e_1_3_2_1_49_1","volume-title":"Towards the Detection of Diffusion Model Deepfakes. CoRR","author":"Ricker Jonas","year":"2022","unstructured":"Jonas Ricker, Simon Damm, Thorsten Holz, and Asja Fischer. 2022. Towards the Detection of Diffusion Model Deepfakes. CoRR (2022), 1--11."},{"key":"e_1_3_2_1_50_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. In CVPR. 10674--10685.","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"e_1_3_2_1_51_1","volume-title":"High-Resolution Image Synthesis with Latent Diffusion Models","author":"Rombach Robin","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In CVPR. IEEE, 10674--10685."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"crossref","unstructured":"Andreas R\u00f6ssler Davide Cozzolino Luisa Verdoliva Christian Riess Justus Thies and Matthias Nie\u00dfner. 2019. FaceForensics: Learning to Detect Manipulated Facial Images. In ICCV. 1--11.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_3_2_1_53_1","volume-title":"Qin Jin, and Baining Guo.","author":"Ruan Ludan","year":"2023","unstructured":"Ludan Ruan, Yiyang Ma, Huan Yang, Huiguo He, Bei Liu, Jianlong Fu, Nicholas Jing Yuan, Qin Jin, and Baining Guo. 2023. MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation. In CVPR. 10219--10228."},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"crossref","unstructured":"Nataniel Ruiz Yuanzhen Li Varun Jampani Yael Pritch Michael Rubinstein and Kfir Aberman. 2023. DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation. In CVPR. 22500--22510.","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"e_1_3_2_1_55_1","volume-title":"Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi.","author":"Saharia Chitwan","year":"2022","unstructured":"Chitwan Saharia, William Chan, Saurabh Saxena, Lala Li, Jay Whang, Emily L. Denton, Seyed Kamyar Seyed Ghasemipour, Raphael Gontijo Lopes, Burcu Karagol Ayan, Tim Salimans, Jonathan Ho, David J. Fleet, and Mohammad Norouzi. 2022. Photorealistic Text-to-Image Diffusion Models with Deep Language Understanding. In NeurIPS. 1--15."},{"key":"e_1_3_2_1_56_1","volume-title":"DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Diffusion Models. CoRR","author":"Sha Zeyang","year":"2022","unstructured":"Zeyang Sha, Zheng Li, Ning Yu, and Yang Zhang. 2022. DE-FAKE: Detection and Attribution of Fake Images Generated by Text-to-Image Diffusion Models. CoRR (2022), 1--14."},{"key":"e_1_3_2_1_57_1","unstructured":"Abhishek Sinha Jiaming Song Chenlin Meng and Stefano Ermon. 2021. D2C: Diffusion-Decoding Models for Few-Shot Conditional Generation. In NeurIPS. 12533--12548."},{"key":"e_1_3_2_1_58_1","unstructured":"Jascha Sohl-Dickstein Eric A. Weiss Niru Maheswaranathan and Surya Ganguli. 2015. Deep Unsupervised Learning using Nonequilibrium Thermodynamics. In ICML. 2256--2265."},{"key":"e_1_3_2_1_59_1","unstructured":"Jiaming Song Chenlin Meng and Stefano Ermon. 2021. Denoising Diffusion Implicit Models. In ICLR. 1--12."},{"key":"e_1_3_2_1_60_1","volume-title":"Evaluating a Synthetic Image Dataset Generated with Stable Diffusion. CoRR","author":"St\u00f6ckl Andreas","year":"2022","unstructured":"Andreas St\u00f6ckl. 2022. Evaluating a Synthetic Image Dataset Generated with Stable Diffusion. CoRR (2022), 1--13."},{"key":"e_1_3_2_1_61_1","volume-title":"Le","author":"Tan Mingxing","year":"2019","unstructured":"Mingxing Tan and Quoc V. Le. 2019. EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks. In ICML. 6105--6114."},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"crossref","unstructured":"Dragos-Constantin T\u00e2ntaru Elisabeta Oneata and Dan Oneata. 2024. Weakly-supervised deepfake localization in diffusion-generated images. In WACV. 6246--6256.","DOI":"10.1109\/WACV57701.2024.00614"},{"key":"e_1_3_2_1_63_1","unstructured":"A\u00e4ron van den Oord Oriol Vinyals and Koray Kavukcuoglu. 2017. Neural Discrete Representation Learning. In NeurIPS. 6306--6315."},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"crossref","unstructured":"O Rebecca Vincent Olusegun Folorunso et al. 2009. A descriptive algorithm for sobel image edge detection. In InSITE. 97--107.","DOI":"10.28945\/3351"},{"key":"e_1_3_2_1_65_1","volume-title":"Efros","author":"Wang Sheng-Yu","year":"2020","unstructured":"Sheng-Yu Wang, Oliver Wang, Richard Zhang, Andrew Owens, and Alexei A. Efros. 2020. CNN-Generated Images Are Surprisingly Easy to Spot... for Now. In CVPR. 8692--8701."},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","unstructured":"Yuan Wang Kun Yu Chen Chen Xiyuan Hu and Silong Peng. 2023. Dynamic Graph Learning with Content-guided Spatial-Frequency Relation Reasoning for Deepfake Detection. In CVPR. 7278--7287.","DOI":"10.1109\/CVPR52729.2023.00703"},{"key":"e_1_3_2_1_67_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. In ICCV. 22445--22455.","DOI":"10.1109\/ICCV51070.2023.02051"},{"key":"e_1_3_2_1_68_1","doi-asserted-by":"crossref","unstructured":"Zhendong Wang Jianmin Bao Wengang Zhou Weilun Wang and Houqiang Li. 2023. AltFreezing for More General Video Face Forgery Detection. In CVPR. 4129--4138.","DOI":"10.1109\/CVPR52729.2023.00402"},{"key":"e_1_3_2_1_69_1","unstructured":"Chen Henry Wu and Fernando De la Torre. 2023. A Latent Space of Stochastic Diffusion Models for Zero-Shot Image Editing and Guidance. In ICCV. 7378--7387."},{"key":"e_1_3_2_1_70_1","doi-asserted-by":"crossref","unstructured":"Xiaoshi Wu Keqiang Sun Feng Zhu Rui Zhao and Hongsheng Li. 2023. Better Aligning Text-to-Image Models with Human Preference. In ICCV. 2096--2105.","DOI":"10.1109\/ICCV51070.2023.00200"},{"key":"e_1_3_2_1_71_1","doi-asserted-by":"crossref","unstructured":"Xi Wu Zhen Xie YuTao Gao and Yu Xiao. 2020. SSTNet: Detecting Manipulated Faces Through Spatial Steganalysis and Temporal Features. In ICASSP. 2952--2956.","DOI":"10.1109\/ICASSP40776.2020.9053969"},{"key":"e_1_3_2_1_72_1","first-page":"3409","article-title":"Mmnet: multi-collaboration and multi-supervision network for sequential deepfake detection","volume":"19","author":"Xia Ruiyang","year":"2024","unstructured":"Ruiyang Xia, Decheng Liu, Jie Li, Lin Yuan, Nannan Wang, and Xinbo Gao. 2024. Mmnet: multi-collaboration and multi-supervision network for sequential deepfake detection. IEEE TIFS, Vol. 19 (2024), 3409--3422.","journal-title":"IEEE TIFS"},{"key":"e_1_3_2_1_73_1","unstructured":"Zhisheng Xiao Karsten Kreis and Arash Vahdat. 2022. Tackling the Generative Learning Trilemma with Denoising Diffusion GANs. In ICLR. 1--15."},{"key":"e_1_3_2_1_74_1","doi-asserted-by":"crossref","unstructured":"Zhengyuan Yang Jianfeng Wang Zhe Gan Linjie Li Kevin Lin Chenfei Wu Nan Duan Zicheng Liu Ce Liu Michael Zeng and Lijuan Wang. 2023. ReCo: Region-Controlled Text-to-Image Generation. In CVPR. 14246--14255.","DOI":"10.1109\/CVPR52729.2023.01369"},{"key":"e_1_3_2_1_75_1","volume-title":"LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. CoRR","author":"Yu Fisher","year":"2015","unstructured":"Fisher Yu, Yinda Zhang, Shuran Song, Ari Seff, and Jianxiong Xiao. 2015. LSUN: Construction of a Large-scale Image Dataset using Deep Learning with Humans in the Loop. CoRR (2015), 1--9."},{"key":"e_1_3_2_1_76_1","volume-title":"FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model. ICCV","author":"Yu Jiwen","year":"2023","unstructured":"Jiwen Yu, Yinhuai Wang, Chen Zhao, Bernard Ghanem, and Jian Zhang. 2023. FreeDoM: Training-Free Energy-Guided Conditional Diffusion Model. ICCV (2023), 23174--23184."},{"key":"e_1_3_2_1_77_1","unstructured":"Guanhua Zhang Jiabao Ji Yang Zhang Mo Yu Tommi S. Jaakkola and Shiyu Chang. 2023. Towards Coherent Image Inpainting Using Denoising Diffusion Implicit Models. In ICML. 41164--41193."},{"key":"e_1_3_2_1_78_1","unstructured":"Qinsheng Zhang and Yongxin Chen. 2023. Fast Sampling of Diffusion Models with Exponential Integrator. In ICLR. 1--12."},{"key":"e_1_3_2_1_79_1","volume-title":"EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations. In NeurIPS. 1--14.","author":"Zhao Min","year":"2022","unstructured":"Min Zhao, Fan Bao, Chongxuan Li, and Jun Zhu. 2022. EGSDE: Unpaired Image-to-Image Translation via Energy-Guided Stochastic Differential Equations. In NeurIPS. 1--14."},{"key":"e_1_3_2_1_80_1","doi-asserted-by":"crossref","unstructured":"Yipin Zhou and Ser-Nam Lim. 2021. Joint Audio-Visual Deepfake Detection. In ICCV. 14800--14809.","DOI":"10.1109\/ICCV48922.2021.01453"},{"key":"e_1_3_2_1_81_1","doi-asserted-by":"crossref","unstructured":"Jiren Zhu Russell Kaplan Justin Johnson and Li Fei-Fei. 2018. HiDDeN: Hiding Data With Deep Networks. In ECCV. 682--697.","DOI":"10.1007\/978-3-030-01267-0_40"},{"key":"e_1_3_2_1_82_1","volume-title":"GenImage: A Million-Scale Benchmark for Detecting AI-Generated Image. CoRR","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. CoRR (2023), 1--11."}],"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\/3664647.3680797","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3680797","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:18:07Z","timestamp":1750295887000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3680797"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":82,"alternative-id":["10.1145\/3664647.3680797","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3680797","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"}}]}}