{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T07:03:48Z","timestamp":1771657428990,"version":"3.50.1"},"reference-count":42,"publisher":"Institution of Engineering and Technology (IET)","issue":"1","license":[{"start":{"date-parts":[[2024,6,9]],"date-time":"2024-06-09T00:00:00Z","timestamp":1717891200000},"content-version":"vor","delay-in-days":160,"URL":"http:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":["ietresearch.onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["IET Biometrics"],"published-print":{"date-parts":[[2024,1]]},"abstract":"<jats:p>Identity\u2010based Deepfake detection methods have the potential to improve the generalization, robustness, and interpretability of the model. However, current identity\u2010based methods either require a reference or can only be used to detect face replacement but not face reenactment. In this paper, we propose a novel Deepfake video detection approach based on identity anomalies. We observe two types of identity anomalies: the inconsistency between clip\u2010level static ID (facial appearance) and clip\u2010level dynamic ID (facial behavior) and the temporal inconsistency of image\u2010level static IDs. Since these two types of anomalies can be detected through self\u2010consistency and do not depend on the manipulation type, our method is a reference\u2010free and manipulation\u2010independent approach. Specifically, our detection network consists of two branches: the static\u2013dynamic ID discrepancy detection branch for the inconsistency between dynamic and static ID and the temporal static ID anomaly detection branch for the temporal anomaly of static ID. We combine the outputs of the two branches by weighted averaging to obtain the final detection result. We also designed two loss functions: the static\u2013dynamic ID matching loss and the dynamic ID constraint loss, to enhance the representation and discriminability of dynamic ID. We conduct experiments on four benchmark datasets and compare our method with the state\u2010of\u2010the\u2010art methods. Results show that our method can detect not only face replacement but also face reenactment, and also has better detection performance over the state\u2010of\u2010the\u2010art methods on unknown datasets. It also has superior robustness against compression. Identity\u2010based features provide a good explanation of the detection results.<\/jats:p>","DOI":"10.1049\/2024\/2280143","type":"journal-article","created":{"date-parts":[[2024,6,10]],"date-time":"2024-06-10T01:05:36Z","timestamp":1717981536000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploring Static\u2013Dynamic ID Matching and Temporal Static ID Inconsistency for Generalizable Deepfake Detection"],"prefix":"10.1049","volume":"2024","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1351-959X","authenticated-orcid":false,"given":"Huimin","family":"She","sequence":"first","affiliation":[{"name":"School of Electronic and Information Engineering South China University of Technology  Guangzhou China  scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7775-3786","authenticated-orcid":false,"given":"Yongjian","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering South China University of Technology  Guangzhou China  scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3907-773X","authenticated-orcid":false,"given":"Beibei","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Electronic and Information Engineering South China University of Technology  Guangzhou China  scut.edu.cn"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4735-6138","authenticated-orcid":false,"given":"Chang-Tsun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Information Technology Deakin University  Geelong Australia  deakin.edu.au"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"265","published-online":{"date-parts":[[2024,6,9]]},"reference":[{"key":"e_1_2_9_1_2","doi-asserted-by":"publisher","DOI":"10.1049\/bme2.12031"},{"key":"e_1_2_9_2_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58610-2"},{"key":"e_1_2_9_3_2","doi-asserted-by":"crossref","unstructured":"LuoY. ZhangY. YanJ. andLiuW. Generalizing face forgery detection with high-frequency features Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2021 Nashville TN USA IEEE 16317\u201316326 https:\/\/doi.org\/10.1109\/CVPR46437.2021.01605.","DOI":"10.1109\/CVPR46437.2021.01605"},{"key":"e_1_2_9_4_2","doi-asserted-by":"crossref","unstructured":"LiuH. LiX. ZhouW. ChenY. HeY. XueH. ZhangW. andYuN. Spatial-phase shallow learning: rethinking face forgery detection in frequency domain 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2021 IEEE 772\u2013781.","DOI":"10.1109\/CVPR46437.2021.00083"},{"key":"e_1_2_9_5_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3198275"},{"key":"e_1_2_9_6_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2022.3233774"},{"key":"e_1_2_9_7_2","doi-asserted-by":"crossref","unstructured":"ZhaoH. WeiT. ZhouW. ZhangW. ChenD. andYuN. Multi-attentional deepfake detection 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2021 IEEE 2185\u20132194.","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"e_1_2_9_8_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3133859"},{"key":"e_1_2_9_9_2","doi-asserted-by":"crossref","unstructured":"ZhengY. BaoJ. ChenD. ZengM. andWenF. Exploring temporal coherence for more general video face forgery detection 2021 IEEE\/CVF International Conference on Computer Vision (ICCV) October 2021 IEEE 15024\u201315034.","DOI":"10.1109\/ICCV48922.2021.01477"},{"key":"e_1_2_9_10_2","doi-asserted-by":"crossref","unstructured":"HaliassosA. VougioukasK. PetridisS. andPanticM. Lips dont lie: a generalisable and robust approach to face forgery detection\u2019 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2021 IEEE 5037\u20135047.","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"e_1_2_9_11_2","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2023.3239223"},{"key":"e_1_2_9_12_2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3238517"},{"key":"e_1_2_9_13_2","doi-asserted-by":"crossref","unstructured":"HaliassosA. MiraR. PetridisS. andPanticM. Leveraging real talking faces via self-supervision for robust forgery detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2022 IEEE 14950\u201314962.","DOI":"10.1109\/CVPR52688.2022.01453"},{"key":"e_1_2_9_14_2","doi-asserted-by":"crossref","unstructured":"AgarwalS. FaridH. El.GaalyT. andLimS. N. Detecting deep-fake videos from appearance and behavior 2020 IEEE International Workshop on Information Forensics and Security (WIFS) December 2020 IEEE 1\u20136.","DOI":"10.1109\/WIFS49906.2020.9360904"},{"key":"e_1_2_9_15_2","doi-asserted-by":"publisher","DOI":"10.1109\/TDSC.2024.3364679"},{"key":"e_1_2_9_16_2","doi-asserted-by":"crossref","unstructured":"DongX. BaoJ. ChenD. ZhangT. ZhangW. YuN. andChenD. Protecting celebrities from deepfake with identity consistency transformer 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2022 IEEE 9458\u20139468.","DOI":"10.1109\/CVPR52688.2022.00925"},{"key":"e_1_2_9_17_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3093446"},{"key":"e_1_2_9_18_2","doi-asserted-by":"crossref","unstructured":"HuangB. WangZ. YangJ. AiJ. ZouQ. WangQ. andYeD. Implicit identity driven deepfake face swapping detection 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2023 IEEE 4490\u20134499.","DOI":"10.1109\/CVPR52729.2023.00436"},{"key":"e_1_2_9_19_2","doi-asserted-by":"crossref","unstructured":"CozzolinoD. R\u00f6sslerA. ThiesJ. Nie\u00dfnerM. andVerdolivaL. Id-reveal: identity-aware deepfake video detection Proceedings of the IEEE\/CVF International Conference on Computer Vision October 2021 IEEE 15108\u201315117.","DOI":"10.1109\/ICCV48922.2021.01483"},{"key":"e_1_2_9_20_2","doi-asserted-by":"publisher","DOI":"10.1049\/bme2.12006"},{"key":"e_1_2_9_21_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109628"},{"key":"e_1_2_9_22_2","doi-asserted-by":"crossref","unstructured":"HeK. FanH. WuY. XieS. andGirshickR. Momentum contrast for unsupervised visual representation learning Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition June 2020 IEEE 9729\u20139738.","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"e_1_2_9_23_2","unstructured":"ChenT. KornblithS. NorouziM. andHintonG. A simple framework for contrastive learning of visual representations International Conference on Machine Learning July 2020 Proceedings of Machine Learning Research 1597\u20131607."},{"key":"e_1_2_9_24_2","doi-asserted-by":"crossref","unstructured":"GaoT. YaoX. andChenD. SimCSE: simple contrastive learning of sentence embeddings Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing November 2021 Association for Computational Linguistics 6894\u20136910.","DOI":"10.18653\/v1\/2021.emnlp-main.552"},{"key":"e_1_2_9_25_2","doi-asserted-by":"crossref","unstructured":"WangY. LiJ. WangH. QianY. WangC. andWuY. Wav2vec-switch: contrastive learning from original-noisy speech pairs for robust speech recognition ICASSP. 2022\u20132022 IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP) May 2022 IEEE 7097\u20137101.","DOI":"10.1109\/ICASSP43922.2022.9746929"},{"key":"e_1_2_9_26_2","doi-asserted-by":"crossref","unstructured":"ChungY. A. ZhangY. HanW. ChiuC. C. QinJ. PangR. andWuY. w2v-bert: combining contrastive learning and masked language modeling for self-supervised speech pre-training 2021 IEEE Automatic Speech Recognition and Understanding Workshop (ASRU) December 2021 IEEE 244\u2013250.","DOI":"10.1109\/ASRU51503.2021.9688253"},{"key":"e_1_2_9_27_2","unstructured":"GrillJ. B. StrubF. Altch\u00e9F. TallecC. RichemondP. H. BuchatskayaE. DoerschC. PiresB. A. GuoZ. D. AzarM. G. PiotB. KavukcuogluK. MunosR. andValkoM. Bootstrap your own latent a new approach to self-supervised learning Proceedings of the 34th International Conference on Neural Information Processing Systems December 2020 Curran Associates Inc.."},{"key":"e_1_2_9_28_2","unstructured":"den OordA. LiY. andVinyalsO. Representation learning with contrastive predictive coding 2018 arXiv preprint arXiv: 180703748."},{"key":"e_1_2_9_29_2","unstructured":"RadfordA. KimJ. W. HallacyC. RameshA. GohG. AgarwalS. SastryG. AskellA. MishkinP. ClarkJ. KruegerG. andSutskeverI. Learning transferable visual models from natural language supervision International Conference on Machine Learning July 2021 Proceedings of Machine Learning Research 8748\u20138763."},{"key":"e_1_2_9_30_2","doi-asserted-by":"crossref","unstructured":"MiechA. AlayracJ. B. SmairaL. LaptevI. SivicJ. andZissermanA. End-to-end learning of visual representations from uncurated instructional videos 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 IEEE 9876\u20139886.","DOI":"10.1109\/CVPR42600.2020.00990"},{"key":"e_1_2_9_31_2","doi-asserted-by":"crossref","unstructured":"WuZ. XiongY. YuS. X. andLinD. Unsupervised feature learning via non-parametric instance discrimination 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2018 IEEE 3733\u20133742.","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_2_9_32_2","doi-asserted-by":"crossref","unstructured":"AnX. DengJ. GuoJ. FengZ. ZhuX. YangJ. andLiuT. Killing two birds with one stone: efficient and robust training of face recognition cnns by partial fc 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2022 IEEE 4032\u20134041.","DOI":"10.1109\/CVPR52688.2022.00401"},{"key":"e_1_2_9_33_2","doi-asserted-by":"crossref","unstructured":"TranD. WangH. TorresaniL. andFeiszliM. Video classification with channel-separated convolutional networks Proceedings of the IEEE\/CVF International Conference on Computer Vision November 2019 IEEE 5552\u20135561.","DOI":"10.1109\/ICCV.2019.00565"},{"key":"e_1_2_9_34_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3076522"},{"key":"e_1_2_9_35_2","doi-asserted-by":"crossref","unstructured":"R\u00f6sslerA. CozzolinoD. VerdolivaL. RiessC. ThiesJ. andNiessnerM. Faceforensics++: learning to detect manipulated facial images 2019 IEEE\/CVF International Conference on Computer Vision (ICCV) November 2019 IEEE 1\u201311.","DOI":"10.1109\/ICCV.2019.00009"},{"key":"e_1_2_9_36_2","doi-asserted-by":"crossref","unstructured":"LiY. YangX. SunP. QiH. andLyuS. Celeb-df: a large-scale challenging dataset for deepfake forensics 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 IEEE 3204\u20133213.","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"e_1_2_9_37_2","unstructured":"DolhanskyB. HowesR. PflaumB. BaramN. andFerrerC. C. The deepfake detection challenge (dfdc) preview dataset 2019 arXiv preprint arXiv: 191008854."},{"key":"e_1_2_9_38_2","doi-asserted-by":"crossref","unstructured":"LiL. BaoJ. YangH. ChenD. andWenF. Advancing high fidelity identity swapping for forgery detection Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2020 IEEE 5074\u20135083.","DOI":"10.1109\/CVPR42600.2020.00512"},{"key":"e_1_2_9_39_2","doi-asserted-by":"crossref","unstructured":"WangH. WangY. ZhouZ. JiX. GongD. ZhouJ. LiZ. andLiuW. Cosface: large margin cosine loss for deep face recognition 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition June 2018 IEEE 5265\u20135274.","DOI":"10.1109\/CVPR.2018.00552"},{"key":"e_1_2_9_40_2","doi-asserted-by":"crossref","unstructured":"DengJ. GuoJ. VerverasE. KotsiaI. andZafeiriouS. Retinaface: single-shot multi-level face localisation in the wild 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) June 2020 IEEE 5202\u20135211.","DOI":"10.1109\/CVPR42600.2020.00525"},{"key":"e_1_2_9_41_2","unstructured":"TanM.andLeQ. Efficientnet: rethinking model scaling for convolutional neural networks International Conference on Machine Learning May 2019 Proceedings of Machine Learning Research 6105\u20136114."},{"key":"e_1_2_9_42_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292039"}],"container-title":["IET Biometrics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/pdf\/10.1049\/2024\/2280143","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,5]],"date-time":"2025-11-05T17:24:32Z","timestamp":1762363472000},"score":1,"resource":{"primary":{"URL":"https:\/\/ietresearch.onlinelibrary.wiley.com\/doi\/10.1049\/2024\/2280143"}},"subtitle":[],"editor":[{"given":"Vincenzo","family":"Conti","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2024,1]]},"references-count":42,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,1]]}},"alternative-id":["10.1049\/2024\/2280143"],"URL":"https:\/\/doi.org\/10.1049\/2024\/2280143","archive":["Portico"],"relation":{},"ISSN":["2047-4938","2047-4946"],"issn-type":[{"value":"2047-4938","type":"print"},{"value":"2047-4946","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1]]},"assertion":[{"value":"2024-01-24","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-05-20","order":2,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2024-06-09","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"2280143"}}