{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:54:15Z","timestamp":1781600055202,"version":"3.54.5"},"publisher-location":"New York, NY, USA","reference-count":40,"publisher":"ACM","license":[{"start":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T00:00:00Z","timestamp":1781568000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,17]]},"DOI":"10.1145\/3785353.3815096","type":"proceedings-article","created":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:11:30Z","timestamp":1781597490000},"page":"17-27","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Patch-Based Reconstruction and Multimodal Residual Learning for Generalized Deepfake Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4773-9617","authenticated-orcid":false,"given":"Niccol\u00f2","family":"Marini","sequence":"first","affiliation":[{"name":"University of Florence, Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7053-0830","authenticated-orcid":false,"given":"Andrea","family":"Ciamarra","sequence":"additional","affiliation":[{"name":"CNIT, Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3471-1196","authenticated-orcid":false,"given":"Roberto","family":"Caldelli","sequence":"additional","affiliation":[{"name":"CNIT, Florence, Italy and Universitas Mercatorum, Rome, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1219-4386","authenticated-orcid":false,"given":"Stefano","family":"Berretti","sequence":"additional","affiliation":[{"name":"University of Florence, Florence, Italy"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,6,16]]},"reference":[{"key":"e_1_3_3_2_2_2","first-page":"1","volume-title":"2018 IEEE international workshop on information forensics and security (WIFS)","author":"Afchar Darius","year":"2018","unstructured":"Darius Afchar, Vincent Nozick, Junichi Yamagishi, and Isao Echizen. 2018. MesoNet: a compact facial video forgery detection network. In 2018 IEEE international workshop on information forensics and security (WIFS). IEEE, 1\u20137."},{"key":"e_1_3_3_2_3_2","doi-asserted-by":"publisher","unstructured":"David Beniaguev. 2022. Synthetic Faces High Quality (SFHQ) dataset. 10.34740\/kaggle\/dsv\/4737549","DOI":"10.34740\/kaggle\/dsv\/4737549"},{"key":"e_1_3_3_2_4_2","first-page":"4113","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Cao Junyi","year":"2022","unstructured":"Junyi Cao, Chao Ma, Taiping Yao, Shen Chen, Shouhong Ding, and Xiaokang Yang. 2022. End-to-end reconstruction-classification learning for face forgery detection. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 4113\u20134122."},{"key":"e_1_3_3_2_5_2","first-page":"111","volume-title":"International Conference on Pattern Recognition","author":"Cappelletti Silvia","year":"2024","unstructured":"Silvia Cappelletti, Lorenzo Baraldi, Federico Cocchi, Marcella Cornia, Lorenzo Baraldi, and Rita Cucchiara. 2024. Adapt to Scarcity: Few-Shot Deepfake Detection via Low-Rank Adaptation. In International Conference on Pattern Recognition. Springer, 111\u2013126."},{"key":"e_1_3_3_2_6_2","first-page":"1251","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Chollet Fran\u00e7ois","year":"2017","unstructured":"Fran\u00e7ois Chollet. 2017. Xception: Deep learning with depthwise separable convolutions. In Proceedings of the IEEE conference on computer vision and pattern recognition. 1251\u20131258."},{"key":"e_1_3_3_2_7_2","unstructured":"Davide Cozzolino Justus Thies Andreas R\u00f6ssler Christian Riess Matthias Nie\u00dfner and Luisa Verdoliva. 2018. Forensictransfer: Weakly-supervised domain adaptation for forgery detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.02510 (2018)."},{"key":"e_1_3_3_2_8_2","doi-asserted-by":"crossref","first-page":"248","DOI":"10.1109\/CVPR.2009.5206848","volume-title":"2009 IEEE conference on computer vision and pattern recognition","author":"Deng Jia","year":"2009","unstructured":"Jia Deng, Wei Dong, Richard Socher, Li-Jia Li, Kai Li, and Li Fei-Fei. 2009. Imagenet: A large-scale hierarchical image database. In 2009 IEEE conference on computer vision and pattern recognition. Ieee, 248\u2013255."},{"key":"e_1_3_3_2_9_2","first-page":"5203","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Deng Jiankang","year":"2020","unstructured":"Jiankang Deng, Jia Guo, Evangelos Ververas, Irene Kotsia, and Stefanos Zafeiriou. 2020. RetinaFace: Single-shot multi-level face localisation in the wild. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 5203\u20135212."},{"key":"e_1_3_3_2_10_2","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Dolhansky Brian","year":"2020","unstructured":"Brian Dolhansky, Russell Howes, Ben Pflaum, Nivan Baram, and Cristian\u00a0Canton Ferrer. 2020. The Deepfake Detection Challenge (DFDC) Dataset. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_3_2_11_2","volume-title":"International Conference on Learning Representations","author":"Dosovitskiy Alexey","year":"2021","unstructured":"Alexey Dosovitskiy, Lucas Beyer, Alexander Kolesnikov, Dirk Weissenborn, Xiaohua Zhai, Thomas Unterthiner, Mostafa Dehghani, Matthias Minderer, Georg Heigold, Sylvain Gelly, Jakob Uszkoreit, and Neil Houlsby. 2021. An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale. In International Conference on Learning Representations. https:\/\/openreview.net\/forum?id=YicbFdNTTy"},{"key":"e_1_3_3_2_12_2","first-page":"7890","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Durall Ricard","year":"2020","unstructured":"Ricard Durall, Margret Keuper, and Janis Keuper. 2020. Watch your up-convolution: Cnn based generative deep neural networks are failing to reproduce spectral distributions. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 7890\u20137899."},{"key":"e_1_3_3_2_13_2","first-page":"3247","volume-title":"International conference on machine learning","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\u20133258."},{"key":"e_1_3_3_2_14_2","first-page":"3247","volume-title":"International conference on machine learning","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\u20133258."},{"key":"e_1_3_3_2_15_2","doi-asserted-by":"crossref","unstructured":"Shichao Gao Ming Xia and Gaobo Yang. 2021. Dual-tree complex wavelet transform-based direction correlation for face forgery detection. Security and Communication Networks 2021 1 (2021) 8661083.","DOI":"10.1155\/2021\/8661083"},{"key":"e_1_3_3_2_16_2","unstructured":"Ian\u00a0J Goodfellow Jean Pouget-Abadie Mehdi Mirza Bing Xu David Warde-Farley Sherjil Ozair Aaron Courville and Yoshua Bengio. 2014. Generative Adversarial Nets. Advances in neural information processing systems 27 (2014)."},{"key":"e_1_3_3_2_17_2","unstructured":"Han Guo Xin Wang and Shiqi Zhang. 2023. Deepfake Detection: A Survey. IEEE Transactions on Pattern Analysis and Machine Intelligence (2023)."},{"key":"e_1_3_3_2_18_2","doi-asserted-by":"crossref","unstructured":"Ahmed\u00a0Abul Hasanaath Hamzah Luqman Raed Katib and Saeed Anwar. 2025. FSBI: Deepfake detection with frequency enhanced self-blended images. Image and Vision Computing 154 (2025) 105418.","DOI":"10.1016\/j.imavis.2025.105418"},{"key":"e_1_3_3_2_19_2","first-page":"16000","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"He Kaiming","year":"2022","unstructured":"Kaiming He, Xinlei Chen, Saining Xie, Yanghao Li, Piotr Doll\u00e1r, and Ross Girshick. 2022. Masked autoencoders are scalable vision learners. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 16000\u201316009."},{"key":"e_1_3_3_2_20_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_2_21_2","unstructured":"Tero Karras Miika Aittala Samuli Laine Erik H\u00e4rk\u00f6nen Janne Hellsten Jaakko Lehtinen and Timo Aila. 2021. Alias-free generative adversarial networks. Advances in neural information processing systems 34 (2021) 852\u2013863."},{"key":"e_1_3_3_2_22_2","first-page":"4401","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Karras Tero","year":"2019","unstructured":"Tero Karras, Samuli Laine, and Timo Aila. 2019. A style-based generator architecture for generative adversarial networks. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 4401\u20134410."},{"key":"e_1_3_3_2_23_2","first-page":"8110","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition","author":"Karras Tero","year":"2020","unstructured":"Tero Karras, Samuli Laine, Miika Aittala, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2020. Analyzing and improving the image quality of StyleGAN. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 8110\u20138119."},{"key":"e_1_3_3_2_24_2","unstructured":"Diederik\u00a0P Kingma and Max Welling. 2013. Auto-encoding variational bayes. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1312.6114 (2013)."},{"key":"e_1_3_3_2_25_2","unstructured":"Pavel Korshunov and S\u00e9bastien Marcel. 2018. Deepfakes: a New Threat to Face Recognition? Assessment and Detection. arXiv preprint arXiv:https:\/\/arXiv.org\/abs\/1812.08685 (2018). arxiv:https:\/\/arXiv.org\/abs\/1812.08685\u00a0[cs.CV]"},{"key":"e_1_3_3_2_26_2","first-page":"17422","volume-title":"Proceedings of the IEEE\/CVF International Conference on Computer Vision","author":"Lee Junho","year":"2025","unstructured":"Junho Lee, Jeongwoo Shin, Hyungwook Choi, and Joonseok Lee. 2025. Latent diffusion models with masked autoencoders. In Proceedings of the IEEE\/CVF International Conference on Computer Vision. 17422\u201317431."},{"key":"e_1_3_3_2_27_2","first-page":"3207","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","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 Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 3207\u20133216."},{"key":"e_1_3_3_2_28_2","first-page":"86","volume-title":"European conference on computer vision","author":"Qian Yuyang","year":"2020","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 European conference on computer vision. Springer, 86\u2013103."},{"key":"e_1_3_3_2_29_2","doi-asserted-by":"crossref","unstructured":"Haonan Qiu Siyu Chen Bei Gan Kun Wang Huafeng Shi Jing Shao and Ziwei Liu. 2023. Few-shot forgery detection via guided adversarial interpolation. Pattern Recognition 144 (2023) 109863.","DOI":"10.1016\/j.patcog.2023.109863"},{"key":"e_1_3_3_2_30_2","first-page":"10684","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition","author":"Rombach Robin","year":"2022","unstructured":"Robin Rombach, Andreas Blattmann, Dominik Lorenz, Patrick Esser, and Bj\u00f6rn Ommer. 2022. High-Resolution Image Synthesis with Latent Diffusion Models. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. 10684\u201310695."},{"key":"e_1_3_3_2_31_2","first-page":"1","volume-title":"Proceedings of the IEEE\/CVF international conference on computer vision","author":"Rossler Andreas","year":"2019","unstructured":"Andreas Rossler, Davide Cozzolino, Luisa Verdoliva, Christian Riess, Justus Thies, and Matthias Nie\u00dfner. 2019. FaceForensics++: Learning to Detect Manipulated Facial Images. In Proceedings of the IEEE\/CVF international conference on computer vision. 1\u201311."},{"key":"e_1_3_3_2_32_2","first-page":"1","volume-title":"ACM SIGGRAPH 2022 Conference Proceedings","author":"Sauer Axel","year":"2022","unstructured":"Axel Sauer, Katja Schwarz, and Andreas Geiger. 2022. StyleGAN-XL: Scaling stylegan to large diverse datasets. In ACM SIGGRAPH 2022 Conference Proceedings. 1\u201310."},{"key":"e_1_3_3_2_33_2","doi-asserted-by":"crossref","unstructured":"Liang Shi Jie Zhang Zhilong Ji Jinfeng Bai and Shiguang Shan. 2025. Real face foundation representation learning for generalized deepfake detection. Pattern Recognition 161 (2025) 111299.","DOI":"10.1016\/j.patcog.2024.111299"},{"key":"e_1_3_3_2_34_2","first-page":"18720","volume-title":"Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition","author":"Shiohara Kaede","year":"2022","unstructured":"Kaede Shiohara and Toshihiko Yamasaki. 2022. Detecting deepfakes with self-blended images. In Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition. 18720\u201318729."},{"key":"e_1_3_3_2_35_2","first-page":"2316","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"36","author":"Sun Ke","year":"2022","unstructured":"Ke Sun, Taiping Yao, Shen Chen, Shouhong Ding, Jilin Li, and Rongrong Ji. 2022. Dual Contrastive Learning for General Face Forgery Detection. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol.\u00a036. 2316\u20132324."},{"key":"e_1_3_3_2_36_2","first-page":"5052","volume-title":"Proceedings of the AAAI Conference on Artificial Intelligence","volume":"38","author":"Tan Chuangchuang","year":"2024","unstructured":"Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, and Yunchao Wei. 2024. Frequency-aware deepfake detection: Improving generalizability through frequency space domain learning. In Proceedings of the AAAI Conference on Artificial Intelligence , Vol.\u00a038. 5052\u20135060."},{"key":"e_1_3_3_2_37_2","doi-asserted-by":"crossref","unstructured":"Justus Thies Michael Zollh\u00f6fer and Matthias Nie\u00dfner. 2019. Deferred Neural Rendering: Image Synthesis using Neural Textures. ACM Transactions on Graphics (TOG) 38 4 (2019) 1\u201312.","DOI":"10.1145\/3306346.3323035"},{"key":"e_1_3_3_2_38_2","first-page":"2387","volume-title":"Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR)","author":"Thies Justus","year":"2016","unstructured":"Justus Thies, Michael Zollh\u00f6fer, Marc Stamminger, Christian Theobalt, and Matthias Nie\u00dfner. 2016. Face2Face: Real-Time Face Capture and Reenactment of RGB Videos. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2387\u20132395."},{"key":"e_1_3_3_2_39_2","doi-asserted-by":"crossref","unstructured":"Moritz Wolter Felix Blanke Raoul Heese and Jochen Garcke. 2022. Wavelet-packets for deepfake image analysis and detection. Machine Learning 111 11 (2022) 4295\u20134327.","DOI":"10.1007\/s10994-022-06225-5"},{"key":"e_1_3_3_2_40_2","first-page":"151","volume-title":"Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security","author":"Xu Nanqing","year":"2023","unstructured":"Nanqing Xu and Weiwei Feng. 2023. Metafake: Few-shot face forgery detection with meta learning. In Proceedings of the 2023 ACM Workshop on Information Hiding and Multimedia Security. 151\u2013156."},{"key":"e_1_3_3_2_41_2","first-page":"391","volume-title":"European conference on computer vision","author":"Zhuang Wanyi","year":"2022","unstructured":"Wanyi Zhuang, Qi Chu, Zhentao Tan, Qiankun Liu, Haojie Yuan, Changtao Miao, Zixiang Luo, and Nenghai Yu. 2022. UIA-ViT: Unsupervised inconsistency-aware method based on vision transformer for face forgery detection. In European conference on computer vision. Springer, 391\u2013407."}],"event":{"name":"IH&MMSec '26: ACM Workshop on Information Hiding and Multimedia Security","location":"Firenze Italy","acronym":"IH&MMSec '26","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2026 ACM Workshop on Information Hiding and Multimedia Security"],"original-title":[],"deposited":{"date-parts":[[2026,6,16]],"date-time":"2026-06-16T08:14:48Z","timestamp":1781597688000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3785353.3815096"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,16]]},"references-count":40,"alternative-id":["10.1145\/3785353.3815096","10.1145\/3785353"],"URL":"https:\/\/doi.org\/10.1145\/3785353.3815096","relation":{},"subject":[],"published":{"date-parts":[[2026,6,16]]},"assertion":[{"value":"2026-06-16","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}