{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:09:55Z","timestamp":1765339795893,"version":"3.46.0"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","funder":[{"name":"National Natural Science Foundation of China under Grant","award":["U21B2048, 62322211, 62376209"],"award-info":[{"award-number":["U21B2048, 62322211, 62376209"]}]},{"name":"Shenzhen Key Technical Projects Under Grant","award":["CJGJZD2022051714160501"],"award-info":[{"award-number":["CJGJZD2022051714160501"]}]},{"name":"the Pioneer and Leading Goose R&D Program of Zhejiang Province","award":["2024C01023"],"award-info":[{"award-number":["2024C01023"]}]},{"name":"Key Laboratory of Intelligent Processing Technology for Digital Music (Zhejiang Conservatory of Music), Ministry of Culture and Tourism","award":["2023DMKLB004"],"award-info":[{"award-number":["2023DMKLB004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,10,27]]},"DOI":"10.1145\/3746027.3755815","type":"proceedings-article","created":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T05:56:43Z","timestamp":1761371803000},"page":"11726-11735","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Frequency-aware Correlation Discovering and Spatial Forgery Clue Distilling for Synthetic Image Detection"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0790-9279","authenticated-orcid":false,"given":"Jiehua","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1943-8219","authenticated-orcid":false,"given":"Liang","family":"Li","sequence":"additional","affiliation":[{"name":"Computer Science, Institute of Computing Technology, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1204-0512","authenticated-orcid":false,"given":"Chenggang","family":"Yan","sequence":"additional","affiliation":[{"name":"Communication Engineering, Hangzhou Dianzi University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2899-0371","authenticated-orcid":false,"given":"Wei","family":"Ke","sequence":"additional","affiliation":[{"name":"School of Software Engineering, Xi'an Jiaotong University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1793-5836","authenticated-orcid":false,"given":"Yihong","family":"Gong","sequence":"additional","affiliation":[{"name":"College of Artificial Intelligence, Xi'an Jiaotong University, Xi'an City, China"}]}],"member":"320","published-online":{"date-parts":[[2025,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1109\/OJSP.2023.3337714"},{"volume-title":"Contrasting deepfakes diffusion via contrastive learning and global-local similarities","author":"Baraldi Lorenzo","key":"e_1_3_2_1_2_1","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 ECCV. Springer, 199-216."},{"key":"e_1_3_2_1_3_1","first-page":"10759","article-title":"FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion","author":"Cazenavette George","year":"2024","unstructured":"George Cazenavette, Avneesh Sud, Thomas Leung, and Ben Usman. 2024. FakeInversion: Learning to Detect Images from Unseen Text-to-Image Models by Inverting Stable Diffusion. In CVPR. 10759-10769.","journal-title":"CVPR."},{"key":"e_1_3_2_1_4_1","volume-title":"DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images. In ICML.","author":"Chen Baoying","year":"2024","unstructured":"Baoying Chen, Jishen Zeng, Jianquan Yang, and Rui Yang. 2024. DRCT: Diffusion Reconstruction Contrastive Training towards Universal Detection of Diffusion Generated Images. In ICML."},{"key":"e_1_3_2_1_5_1","volume-title":"LDR-Net: A Novel Framework for AI-generated Image Detection via Localized Discrepancy Representation. arXiv preprint arXiv:2501.13475","author":"Chen JiaXin","year":"2025","unstructured":"JiaXin Chen, Miao Hu, DengYong Zhang, Yun Song, and Xin Liao. 2025. LDR-Net: A Novel Framework for AI-generated Image Detection via Localized Discrepancy Representation. arXiv preprint arXiv:2501.13475 (2025)."},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16193"},{"key":"e_1_3_2_1_7_1","unstructured":"Kyunghyun Cho B van Merrienboer Caglar Gulcehre F Bougares H Schwenk and Yoshua Bengio. 2014. Learning phrase representations using RNN encoder-decoder for statistical machine translation. In EMNLP."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-024-2762-5"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-024-2753-3"},{"key":"e_1_3_2_1_10_1","first-page":"7890","article-title":"Watch your up-convolution: Cnn based generative deep neural networks are failing to reproduce spectral distributions","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 CVPR. 7890-7899.","journal-title":"CVPR."},{"key":"e_1_3_2_1_11_1","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","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 ICML. PMLR, 3247-3258.","journal-title":"ICML. PMLR"},{"key":"e_1_3_2_1_12_1","unstructured":"John Guibas Morteza Mardani Zongyi Li Andrew Tao Anima Anandkumar and Bryan Catanzaro. 2021. Efficient Token Mixing for Transformers via Adaptive Fourier Neural Operators. In ICLR."},{"key":"e_1_3_2_1_13_1","first-page":"770","article-title":"Deep residual learning for image recognition","author":"He Kaiming","year":"2016","unstructured":"Kaiming He, Xiangyu Zhang, Shaoqing Ren, and Jian Sun. 2016. Deep residual learning for image recognition. In CVPR. 770-778.","journal-title":"CVPR."},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-024-2755-x"},{"key":"e_1_3_2_1_15_1","first-page":"1006","article-title":"Clipping the deception: Adapting vision-language models for universal deepfake detection","author":"Khan Sohail Ahmed","year":"2024","unstructured":"Sohail Ahmed Khan and Duc-Tien Dang-Nguyen. 2024. Clipping the deception: Adapting vision-language models for universal deepfake detection. In ICMR. 1006-1015.","journal-title":"ICMR."},{"key":"e_1_3_2_1_16_1","volume-title":"Moe-ffd: Mixture of experts for generalized and parameter-efficient face forgery detection. arXiv preprint arXiv:2404.08452","author":"Kong Chenqi","year":"2024","unstructured":"Chenqi Kong, Anwei Luo, Peijun Bao, Yi Yu, Haoliang Li, Zengwei Zheng, Shiqi Wang, and Alex C Kot. 2024. Moe-ffd: Mixture of experts for generalized and parameter-efficient face forgery detection. arXiv preprint arXiv:2404.08452 (2024)."},{"volume-title":"Leveraging representations from intermediate encoder-blocks for synthetic image detection","author":"Koutlis Christos","key":"e_1_3_2_1_17_1","unstructured":"Christos Koutlis and Symeon Papadopoulos. 2024. Leveraging representations from intermediate encoder-blocks for synthetic image detection. In ECCV. Springer, 394-411."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3597267"},{"key":"e_1_3_2_1_19_1","volume-title":"Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective. arXiv","author":"Li Ouxiang","year":"2024","unstructured":"Ouxiang Li, Jiayin Cai, Yanbin Hao, Xiaolong Jiang, Yao Hu, and Fuli Feng. 2024a. Improving Synthetic Image Detection Towards Generalization: An Image Transformation Perspective. arXiv (2024)."},{"key":"e_1_3_2_1_20_1","volume-title":"Revealing the Implicit Noise-based Imprint of Generative Models. arXiv preprint arXiv:2503.09314","author":"Li Xinghan","year":"2025","unstructured":"Xinghan Li, Jingjing Chen, Yue Yu, Xue Song, Haijun Shan, and Yu-Gang Jiang. 2025a. Revealing the Implicit Noise-based Imprint of Generative Models. arXiv preprint arXiv:2503.09314 (2025)."},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02091-x"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3516561"},{"key":"e_1_3_2_1_23_1","first-page":"10770","article-title":"Forgery-aware adaptive transformer for generalizable synthetic image detection","author":"Liu Huan","year":"2024","unstructured":"Huan Liu, Zichang Tan, Chuangchuang Tan, Yunchao Wei, Jingdong Wang, and Yao Zhao. 2024. Forgery-aware adaptive transformer for generalizable synthetic image detection. In CVPR. 10770-10780.","journal-title":"CVPR."},{"key":"e_1_3_2_1_24_1","first-page":"11525","article-title":"Object-centric learning with slot attention","volume":"33","author":"Locatello Francesco","year":"2020","unstructured":"Francesco Locatello, Dirk Weissenborn, Thomas Unterthiner, Aravindh Mahendran, Georg Heigold, Jakob Uszkoreit, Alexey Dosovitskiy, and Thomas Kipf. 2020. Object-centric learning with slot attention. NeurIPS, Vol. 33 (2020), 11525-11538.","journal-title":"NeurIPS"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-024-2748-3"},{"key":"e_1_3_2_1_26_1","first-page":"17006","article-title":"LaRE^ 2","author":"Luo Yunpeng","year":"2024","unstructured":"Yunpeng Luo, Junlong Du, Ke Yan, and Shouhong Ding. 2024. LaRE^ 2: Latent Reconstruction Error Based Method for Diffusion-Generated Image Detection. In CVPR. 17006-17015.","journal-title":"In CVPR."},{"key":"e_1_3_2_1_27_1","unstructured":"RuiPeng Ma Jinhao Duan Fei Kong Xiaoshuang Shi and Kaidi Xu. 2024. Exposing the Fake: Effective Diffusion-Generated Images Detection. In ICML."},{"key":"e_1_3_2_1_28_1","first-page":"24480","article-title":"Towards universal fake image detectors that generalize across generative models","author":"Ojha Utkarsh","year":"2023","unstructured":"Utkarsh Ojha, Yuheng Li, and Yong Jae Lee. 2023. Towards universal fake image detectors that generalize across generative models. In CVPR. 24480-24489.","journal-title":"CVPR."},{"volume-title":"Thinking in frequency: Face forgery detection by mining frequency-aware clues","author":"Qian Yuyang","key":"e_1_3_2_1_29_1","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. Springer, 86-103."},{"key":"e_1_3_2_1_30_1","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","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 ICML. 8748-8763.","journal-title":"ICML."},{"key":"e_1_3_2_1_31_1","first-page":"9130","article-title":"AEROBLADE","author":"Ricker Jonas","year":"2024","unstructured":"Jonas Ricker, Denis Lukovnikov, and Asja Fischer. 2024. AEROBLADE: Training-Free Detection of Latent Diffusion Images Using Autoencoder Reconstruction Error. In CVPR. 9130-9140.","journal-title":"In CVPR."},{"key":"e_1_3_2_1_32_1","unstructured":"snopes. 2024. https:\/\/www.snopes.com\/fact-check\/trump-hitler-photo\/?collection=468705."},{"volume-title":"An information theoretic approach for attention-driven face forgery detection","author":"Sun Ke","key":"e_1_3_2_1_33_1","unstructured":"Ke Sun, Hong Liu, Taiping Yao, Xiaoshuai Sun, Shen Chen, Shouhong Ding, and Rongrong Ji. 2022. An information theoretic approach for attention-driven face forgery detection. In ECCV. Springer, 111-127."},{"key":"e_1_3_2_1_34_1","volume-title":"C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection. AAAI","author":"Tan Chuangchuang","year":"2025","unstructured":"Chuangchuang Tan, Renshuai Tao, Huan Liu, Guanghua Gu, Baoyuan Wu, Yao Zhao, and Yunchao Wei. 2025. C2P-CLIP: Injecting Category Common Prompt in CLIP to Enhance Generalization in Deepfake Detection. AAAI (2025)."},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i5.28310"},{"key":"e_1_3_2_1_36_1","first-page":"28130","article-title":"Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection","author":"Tan Chuangchuang","year":"2024","unstructured":"Chuangchuang Tan, Yao Zhao, Shikui Wei, Guanghua Gu, Ping Liu, and Yunchao Wei. 2024b. Rethinking the Up-Sampling Operations in CNN-based Generative Network for Generalizable Deepfake Detection. In CVPR. 28130-28139.","journal-title":"CVPR."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3546845"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3365104"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11431-024-2732-9"},{"key":"e_1_3_2_1_40_1","first-page":"8695","article-title":"CNN-generated images are surprisingly easy to spot... for now","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. 8695-8704.","journal-title":"CVPR."},{"key":"e_1_3_2_1_41_1","volume-title":"WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection. International Journal of Computer Vision","author":"Wang Yuan","year":"2024","unstructured":"Yuan Wang, Chen Chen, Ning Zhang, and Xiyuan Hu. 2024b. WATCHER: Wavelet-Guided Texture-Content Hierarchical Relation Learning for Deepfake Detection. International Journal of Computer Vision (2024), 1-22."},{"key":"e_1_3_2_1_42_1","first-page":"22445","article-title":"Dire for diffusion-generated image detection","author":"Wang Zhendong","year":"2023","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.","journal-title":"ICCV."},{"key":"e_1_3_2_1_43_1","volume-title":"Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum. arXiv preprint arXiv:2503.08484","author":"Xiao Shengpeng","year":"2025","unstructured":"Shengpeng Xiao, Yuanfang Guo, Heqi Peng, Zeming Liu, Liang Yang, and Yunhong Wang. 2025. Generalizable AI-Generated Image Detection Based on Fractal Self-Similarity in the Spectrum. arXiv preprint arXiv:2503.08484 (2025)."},{"key":"e_1_3_2_1_44_1","volume-title":"A sanity check for ai-generated image detection. ICLR","author":"Yan Shilin","year":"2025","unstructured":"Shilin Yan, Ouxiang Li, Jiayin Cai, Yanbin Hao, Xiaolong Jiang, Yao Hu, and Weidi Xie. 2025. A sanity check for ai-generated image detection. ICLR (2025)."},{"key":"e_1_3_2_1_45_1","volume-title":"Effort: Efficient Orthogonal Modeling for Generalizable AI-Generated Image Detection. arXiv preprint arXiv:2411.15633","author":"Yan Zhiyuan","year":"2024","unstructured":"Zhiyuan Yan, Jiangming Wang, Zhendong Wang, Peng Jin, Ke-Yue Zhang, Shen Chen, Taiping Yao, Shouhong Ding, Baoyuan Wu, and Li Yuan. 2024. Effort: Efficient Orthogonal Modeling for Generalizable AI-Generated Image Detection. arXiv preprint arXiv:2411.15633 (2024)."},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1049\/cje.2021.00.455"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3432099"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.23919\/cje.2022.00.414"},{"key":"e_1_3_2_1_49_1","first-page":"2921","article-title":"Learning deep features for discriminative localization","author":"Zhou Bolei","year":"2016","unstructured":"Bolei Zhou, Aditya Khosla, Agata Lapedriza, Aude Oliva, and Antonio Torralba. 2016. Learning deep features for discriminative localization. In CVPR. 2921-2929.","journal-title":"CVPR."},{"key":"e_1_3_2_1_50_1","volume-title":"NeurIPS","volume":"36","author":"Zhu Mingjian","year":"2024","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. NeurIPS, Vol. 36 (2024)."}],"event":{"name":"MM '25: The 33rd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Dublin Ireland","acronym":"MM '25"},"container-title":["Proceedings of the 33rd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3746027.3755815","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,10]],"date-time":"2025-12-10T04:07:07Z","timestamp":1765339627000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3746027.3755815"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,27]]},"references-count":50,"alternative-id":["10.1145\/3746027.3755815","10.1145\/3746027"],"URL":"https:\/\/doi.org\/10.1145\/3746027.3755815","relation":{},"subject":[],"published":{"date-parts":[[2025,10,27]]},"assertion":[{"value":"2025-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}