{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T18:10:03Z","timestamp":1760379003404,"version":"build-2065373602"},"reference-count":80,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"name":"Japan Society for the Promotion of Science (JSPS) KAKENHI","award":["JP21H04907","JP24H00732"],"award-info":[{"award-number":["JP21H04907","JP24H00732"]}]},{"name":"Japan Science and Technology Agency (JST) Core Research for Evolutional Science and Technology","award":["JPMJCR20D3"],"award-info":[{"award-number":["JPMJCR20D3"]}]},{"name":"AIP challenge program, by JST Advanced Integrated Intelligence Platform (AIP) Acceleration","award":["JPMJCR24U3"],"award-info":[{"award-number":["JPMJCR24U3"]}]},{"name":"JST K Program","award":["JPMJKP24C2 Japan"],"award-info":[{"award-number":["JPMJKP24C2 Japan"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2025.3617447","type":"journal-article","created":{"date-parts":[[2025,10,3]],"date-time":"2025-10-03T17:26:17Z","timestamp":1759512377000},"page":"173909-173922","source":"Crossref","is-referenced-by-count":0,"title":["GenPure: Foundation-Model-Guided Multi-Stage Purification Framework for Black-Box Evasion of Deepfake Detectors"],"prefix":"10.1109","volume":"13","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-7929-9003","authenticated-orcid":false,"given":"Yuyang","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Information and Communication Engineering, The University of Tokyo, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7723-4591","authenticated-orcid":false,"given":"Ching-Chun","family":"Chang","sequence":"additional","affiliation":[{"name":"National Institute of Informatics, Tokyo, Japan"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4908-1860","authenticated-orcid":false,"given":"Isao","family":"Echizen","sequence":"additional","affiliation":[{"name":"Department of Information and Communication Engineering, The University of Tokyo, Tokyo, Japan"}]}],"member":"263","reference":[{"volume-title":"Ranger: A Synergistic Optimizer","year":"2019","author":"Wright","key":"ref1"},{"volume-title":"Synthetic Faces High Quality (SFHQ) Dataset","year":"2022","author":"Beniaguev","key":"ref2"},{"article-title":"Progressive growing of GANs for improved quality, stability, and variation","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Karras","key":"ref3"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00244"},{"article-title":"Large scale GAN training for high fidelity natural image synthesis","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Brock","key":"ref6"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00916"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.244"},{"key":"ref9","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Ho"},{"key":"ref10","first-page":"8162","article-title":"Improved denoising diffusion probabilistic models","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Nichol"},{"key":"ref11","first-page":"8780","article-title":"Diffusion models beat GANs on image synthesis","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Dhariwal"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3425780"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"ref15","first-page":"38","article-title":"Protecting world leaders against deep fakes","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops (CVPRW)","author":"Agarwal"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/MIPR.2019.00103"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00765"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2_6"},{"key":"ref20","first-page":"3247","article-title":"Leveraging frequency analysis for deep fake image recognition","volume-title":"Proc. Int. Conf. Mach. Learn. (ICML)","author":"Frank"},{"key":"ref21","first-page":"3022","article-title":"Fourier spectrum discrepancies in deep network generated images","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"33","author":"Durall"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW58289.2023.00070"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/IJCB62174.2024.10744491"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2020\/476"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3278310"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02345"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01165"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02657"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681535"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00103"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2025.110276"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3207310"},{"key":"ref36","article-title":"Vulnerabilities in AI-generated image detection: The challenge of adversarial attacks","author":"Diao","year":"2024","journal-title":"arXiv:2407.20836"},{"key":"ref37","article-title":"Unmasking synthetic realities in generative AI: A comprehensive review of adversarially robust deepfake detection systems","author":"Khan","year":"2025","journal-title":"arXiv:2507.21157"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP48485.2024.10448251"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413732"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01181"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2023.3241604"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2024.121267"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/WACVW60836.2024.00115"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3325427"},{"key":"ref45","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222083"},{"key":"ref49","first-page":"4487","article-title":"Generative adversarial transformers","volume-title":"Proc. 38th Int. Conf. Mach. Learn. (ICML)","author":"Hudson"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.168"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00432"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00347"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01132"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2106.12423"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01405"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"ref58","article-title":"GLIDE: Towards photorealistic image generation and editing with text-guided diffusion models","author":"Nichol","year":"2021","journal-title":"arXiv:2112.10741"},{"key":"ref59","article-title":"Diffusion-GAN: Training GANs with diffusion","author":"Wang","year":"2022","journal-title":"arXiv:2206.02262"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01049"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.05957"},{"key":"ref63","first-page":"2203","article-title":"MMD GAN: Towards deeper understanding of moment matching network","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","volume":"30","author":"Li"},{"key":"ref64","article-title":"The Cramer distance as a solution to biased Wasserstein gradients","author":"Bellemare","year":"2017","journal-title":"arXiv:1705.10743"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00009"},{"issue":"1","key":"ref66","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"J. Mach. Learn. Res."},{"article-title":"Diffusion-GAN: Training GANs with diffusion","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Wang","key":"ref67"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref69","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"van der Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1080\/14786440109462720"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TSP.2006.881199"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2022.103525"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2020.3004708"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3510355"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3415415"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/7503.003.0022"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3441821"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.7717\/peerj-cs.2127"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2024.123732"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3390\/jimaging11030073"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/11192309.pdf?arnumber=11192309","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T17:41:54Z","timestamp":1760377314000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11192309\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3617447","relation":{},"ISSN":["2169-3536"],"issn-type":[{"type":"electronic","value":"2169-3536"}],"subject":[],"published":{"date-parts":[[2025]]}}}