{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,2]],"date-time":"2026-07-02T04:07:33Z","timestamp":1782965253119,"version":"3.54.5"},"reference-count":61,"publisher":"IEEE","license":[{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,3,6]],"date-time":"2026-03-06T00:00:00Z","timestamp":1772755200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2026,3,6]]},"DOI":"10.1109\/wacv61042.2026.00601","type":"proceedings-article","created":{"date-parts":[[2026,5,5]],"date-time":"2026-05-05T19:59:32Z","timestamp":1778011172000},"page":"6215-6225","source":"Crossref","is-referenced-by-count":1,"title":["AuthGuard: Generalizable Deepfake Detection via Language Guidance"],"prefix":"10.1109","author":[{"given":"Guangyu","family":"Shen","sequence":"first","affiliation":[{"name":"Purdue University"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhihua","family":"Li","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiang","family":"Xu","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Tianchen","family":"Zhao","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheng","family":"Zhang","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongsheng","family":"An","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhuowen","family":"Tu","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yifan","family":"Xing","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qin","family":"Zhang","sequence":"additional","affiliation":[{"name":"AWS DS3"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Phi-3 technical report: A highly capable language model locally on your phone","author":"Abdin","year":"2024"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/SP54263.2024.00194"},{"key":"ref3","article-title":"Gpt-4 technical report","author":"Achiam","year":"2023"},{"key":"ref4","first-page":"65","article-title":"Meteor: An automatic metric for mt evaluation with improved correlation with human judgments","volume-title":"Proceedings of the acl workshop on intrinsic and extrinsic evaluation measures for machine translation and\/or summarization","author":"Banerjee"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00408"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00575"},{"key":"ref7","article-title":"Antifakeprompt: Prompt-tuned vision-language models are fake image detectors","author":"Chang","year":"2023"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00045"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01815"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02283"},{"key":"ref11","author":"Chiang","year":"2023","journal-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90%* chatgpt quality"},{"key":"ref12","article-title":"The deepfake detection challenge (dfdc) dataset","author":"Dolhansky","year":"2020"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3422622"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1073\/pnas.2110013119"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00019"},{"key":"ref16","first-page":"6840","author":"Ho","year":"2020","journal-title":"Denoising diffusion probabilistic models"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00820"},{"key":"ref19","article-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref20","article-title":"Deepfake detection: humans vs. machines","author":"Korshunov","year":"2020"},{"key":"ref21","article-title":"Llava-onevision: Easy visual task transfer","author":"Li","year":"2024"},{"key":"ref22","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"International Conference on machine learning","author":"Li"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00505"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"ref25","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","author":"Lin","year":"2004","journal-title":"Text summarization branches out"},{"key":"ref26","first-page":"104","article-title":"Fake it till you make it: Curricular dynamic forgery augmentations towards general deepfake detection","volume-title":"European Conference on computer vision","author":"Lin"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1516"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref30","article-title":"Roberta: A robustly optimized bert pretraining approach","author":"Liu","year":"2019"},{"key":"ref31","article-title":"Ursa: Understanding and verifying chain-of-thought reasoning in multi-modal mathematics","author":"Luo","year":"2025"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"ref33","year":"2024","journal-title":"Llama 3.2: Revolutionizing edge AI and vision with open, customizable models"},{"key":"ref34","journal-title":"Detect fakes: Overview"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01647"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00011"},{"key":"ref37","article-title":"X-instructblip: A framework for aligning x-modal instruction-aware representations to llms and emergent cross-modal reasoning","author":"Panagopoulou","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3801962"},{"key":"ref40","article-title":"Sdxl: Improving latent diffusion models for high-resolution image synthesis","author":"Podell","year":"2023"},{"key":"ref41","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on machine learning","author":"Radford"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00009"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1833"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00700"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01816"},{"key":"ref48","first-page":"402","article-title":"Real appearance modeling for more general deepfake detection","volume-title":"European Conference on Computer Vision","author":"Tian"},{"key":"ref49","article-title":"Instruction tuning on large language models to improve reasoning performance","author":"Vaillancourt","year":"2024","journal-title":"Authorea Preprints"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref51","article-title":"Principles of designing robust remote face anti-spoofing systems","author":"Xu","year":"2024"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02071"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02048"},{"key":"ref54","article-title":"Deepfakebench: A comprehensive benchmark of deepfake detection","author":"Yan","year":"2023"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00858"},{"key":"ref56","article-title":"Df40: Toward next-generation deepfake detection","author":"Yan","year":"2024"},{"key":"ref57","article-title":"Ip-adapter: Text compatible image prompt adapter for text-to-image diffusion models","author":"Ye","year":"2023"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02191"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00097"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73223-2_22"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01475"}],"event":{"name":"2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)","location":"Tucson, AZ, USA","start":{"date-parts":[[2026,3,6]]},"end":{"date-parts":[[2026,3,10]]}},"container-title":["2026 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11491838\/11491925\/11492581.pdf?arnumber=11492581","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T06:16:52Z","timestamp":1778048212000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11492581\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,6]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/wacv61042.2026.00601","relation":{},"subject":[],"published":{"date-parts":[[2026,3,6]]}}}