{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,8]],"date-time":"2026-06-08T14:52:46Z","timestamp":1780930366725,"version":"3.54.1"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"26","license":[{"start":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T00:00:00Z","timestamp":1706486400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T00:00:00Z","timestamp":1706486400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimed Tools Appl"],"DOI":"10.1007\/s11042-024-18130-1","type":"journal-article","created":{"date-parts":[[2024,1,29]],"date-time":"2024-01-29T07:02:33Z","timestamp":1706511753000},"page":"68063-68086","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["D-Fence layer: an ensemble framework for comprehensive deepfake detection"],"prefix":"10.1007","volume":"83","author":[{"given":"Asha","family":"S","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Vinod","family":"P","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Irene","family":"Amerini","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Varun G.","family":"Menon","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,29]]},"reference":[{"issue":"4","key":"18130_CR1","doi-asserted-by":"publisher","first-page":"3974","DOI":"10.1007\/s10489-022-03766-z","volume":"53","author":"M Masood","year":"2023","unstructured":"Masood M, Nawaz M, Malik KM, Javed A, Irtaza A, Malik H (2023) Deepfakes generation and detection: state-of-the-art, open challenges, countermeasures, and way forward. Appl Intell 53(4):3974\u20134026","journal-title":"Appl Intell"},{"issue":"4","key":"18130_CR2","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn S, Seitz SM, Kemelmacher-Shlizerman I (2017) Synthesizing obama: learning lip sync from audio. ACM Trans Graph 36(4):1\u201313","journal-title":"ACM Trans Graph"},{"key":"18130_CR3","unstructured":"News Desk (2020) Fabricated video of vladimir putin takes twitter by storm. https:\/\/www.globalvillagespace.com\/fabricated-video-of-vladimir-putin-takes-twitter-by-storm\/. Accessed 27 Aug 2023"},{"key":"18130_CR4","doi-asserted-by":"crossref","unstructured":"Prajwal K, Mukhopadhyay R, Namboodiri VP, Jawahar C (2020) A lip sync expert is all you need for speech to lip generation in the wild. In: Proceedings of the 28th ACM international conference on multimedia, pp 484\u2013492","DOI":"10.1145\/3394171.3413532"},{"key":"18130_CR5","first-page":"4480","volume":"31","author":"Y Jia","year":"2018","unstructured":"Jia Y, Zhang Y, Weiss R, Wang Q, Shen J, Ren F, Nguyen P, Pang R, Lopez Moreno I, Wu Y et al (2018) Transfer learning from speaker verification to multispeaker text-to-speech synthesis. Adv Neural Inf Process Syst 31:4480\u20134490","journal-title":"Adv Neural Inf Process Syst"},{"key":"18130_CR6","unstructured":"Youtube. Bbc has wrong subtitles for trump\u2019s inauguration. [Online]. Available https:\/\/www.youtube.com\/shorts\/4jtzzAQgswo"},{"key":"18130_CR7","unstructured":"WatchMojo. Another top 10 deepfake videos. [Online]. Available https:\/\/www.youtube.com\/watch?v=DGSR9j5A8xc&list=RDCMUCaWd5&index=1"},{"issue":"7","key":"18130_CR8","doi-asserted-by":"publisher","first-page":"263","DOI":"10.3390\/info12070263","volume":"12","author":"T Liu","year":"2021","unstructured":"Liu T, Yan D, Wang R, Yan N, Chen G (2021) Identification of fake stereo audio using svm and cnn. Information 12(7):263","journal-title":"Information"},{"key":"18130_CR9","unstructured":"Korshunov P, Marcel S (2018) Deepfakes: a new threat to face recognition? Assessment and detection. arXiv preprint arXiv:1812.08685"},{"key":"18130_CR10","unstructured":"Li Y, Lyu S (2018) Exposing deepfake videos by detecting face warping artifacts.arXiv preprint arXiv:1811.00656"},{"key":"18130_CR11","doi-asserted-by":"crossref","unstructured":"Rossler A, Cozzolino D, Verdoliva L, Riess C, Thies J, Nie\u00dfner M (2019) Faceforensics++: learning to detect manipulated facial images. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 1\u201311","DOI":"10.1109\/ICCV.2019.00009"},{"key":"18130_CR12","unstructured":"Dufour\u00a0N, Gully\u00a0A (2020) Contributing data to deepfake detection research. https:\/\/rb.gy\/p4s5u6. Accessed 27 Aug 2023"},{"key":"18130_CR13","doi-asserted-by":"crossref","unstructured":"Li Y, Yang X, Sun P, Qi H, Lyu S (2020) Celeb-df: a large-scale challenging dataset for deepfake forensics. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 3207\u20133216","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"18130_CR14","unstructured":"Dolhansky B, Howes R, Pflaum B, Baram N, Ferrer CC (2019) The deepfake detection challenge (dfdc) preview dataset, arXiv preprint arXiv:1910.08854"},{"key":"18130_CR15","unstructured":"Khalid H, Tariq S, Kim M, Woo SS (2021) Fakeavceleb: a novel audio-video multimodal deepfake dataset. 35th Conference on Neural Information Processing Systems (NeurIPS 2021)"},{"key":"18130_CR16","doi-asserted-by":"crossref","unstructured":"Asha S, Vinod P, Menon VG (2023) Mmdfd- a multimodal custom dataset for deepfake detection. In: IC3\u20132023: Proceedings of the 2023 Fifteenth International Conference on Contemporary Computing. ACM, pp 322\u2013327","DOI":"10.1145\/3607947.3608013"},{"key":"18130_CR17","doi-asserted-by":"crossref","unstructured":"G\u00fcera D, Delp EJ (2018) Deepfake video detection using recurrent neural networks. In: 2018 15th IEEE international conference on advanced video and signal based surveillance (AVSS). IEEE, pp 1\u20136","DOI":"10.1109\/AVSS.2018.8639163"},{"issue":"16","key":"18130_CR18","doi-asserted-by":"publisher","first-page":"5413","DOI":"10.3390\/s21165413","volume":"21","author":"A Ismail","year":"2021","unstructured":"Ismail A, Elpeltagy M, Zaki MS, Eldahshan K (2021) A new deep learning-based methodology for video deepfake detection using xgboost. Sensors 21(16):5413","journal-title":"Sensors"},{"key":"18130_CR19","doi-asserted-by":"crossref","unstructured":"Khan SA, Dai H (2021) Video transformer for deepfake detection with incremental learning. In: Proceedings of the 29th ACM international conference on multimedia, pp 1821\u20131828","DOI":"10.1145\/3474085.3475332"},{"key":"18130_CR20","doi-asserted-by":"crossref","unstructured":"Hu J, Liao X, Liang J, Zhou W, Qin Z (2022) Finfer: frame inference-based deepfake detection for high-visual-quality videos. In: Proceedings of the AAAI conference on artificial intelligence, vol 36, no 1, pp 951\u2013959","DOI":"10.1609\/aaai.v36i1.19978"},{"key":"18130_CR21","doi-asserted-by":"crossref","unstructured":"Dong S, Wang J, Liang J, Fan H, Ji R (2022) Explaining deepfake detection by analysing image matching. In: European conference on computer vision. Springer, pp 18\u201335","DOI":"10.1007\/978-3-031-19781-9_2"},{"key":"18130_CR22","doi-asserted-by":"crossref","unstructured":"Coccomini DA, Messina N, Gennaro C, Falchi F (2022) Combining efficientnet and vision transformers for video deepfake detection. In: International conference on image analysis and processing. Springer, pp 219\u2013229","DOI":"10.1007\/978-3-031-06433-3_19"},{"key":"18130_CR23","doi-asserted-by":"crossref","unstructured":"Saikia P, Dholaria D, Yadav P, Patel V, Roy M (2022) A hybrid cnn-lstm model for video deepfake detection by leveraging optical flow features. In: 2022 International Joint Conference on Neural Networks (IJCNN). IEEE, pp 1\u20137","DOI":"10.1109\/IJCNN55064.2022.9892905"},{"key":"18130_CR24","doi-asserted-by":"publisher","first-page":"211","DOI":"10.1016\/j.procs.2023.01.283","volume":"219","author":"M Mcuba","year":"2023","unstructured":"Mcuba M, Singh A, Ikuesan RA, Venter H (2023) The effect of deep learning methods on deepfake audio detection for digital investigation. Procedia Comput Sci 219:211\u2013219","journal-title":"Procedia Comput Sci"},{"key":"18130_CR25","doi-asserted-by":"crossref","unstructured":"Ulutas G, Tahaoglu G, Ustubioglu B (2023) Deepfake audio detection with vision transformer based method. In: 2023 46th International Conference on Telecommunications and Signal Processing (TSP), IEEE, pp 244\u2013247","DOI":"10.1109\/TSP59544.2023.10197715"},{"key":"18130_CR26","doi-asserted-by":"crossref","unstructured":"Wani TM, Amerini I (2023) Deepfakes audio detection leveraging audio spectrogram and convolutional neural networks. In: International conference on image analysis and processing. Springer, pp 156\u2013167","DOI":"10.1007\/978-3-031-43153-1_14"},{"key":"18130_CR27","doi-asserted-by":"crossref","unstructured":"Reimao R, Tzerpos V (2019) For: a dataset for synthetic speech detection. In: 2019 International Conference on Speech Technology and Human-Computer Dialogue (SpeD). IEEE, pp 1\u201310","DOI":"10.1109\/SPED.2019.8906599"},{"key":"18130_CR28","doi-asserted-by":"crossref","unstructured":"Cozzolino D, Pianese A, Nie\u00dfner M, Verdoliva L (2023) Audio-visual person-of-interest deepfake detection. In: Proceedings of the IEEE\/CVF conference on computer vision and pattern recognition, pp 943\u2013952","DOI":"10.1109\/CVPRW59228.2023.00101"},{"key":"18130_CR29","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.110124","volume":"136","author":"H Ilyas","year":"2023","unstructured":"Ilyas H, Javed A, Malik KM (2023) Avfakenet: a unified end-to-end dense swin transformer deep learning model for audio-visual deepfakes detection. Appl Soft Comput 136:110124","journal-title":"Appl Soft Comput"},{"key":"18130_CR30","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1109\/TIFS.2023.3262148","volume":"18","author":"W Yang","year":"2023","unstructured":"Yang W, Zhou X, Chen Z, Guo B, Ba Z, Xia Z, Cao X, Ren K (2023) Avoid-df: audio-visual joint learning for detecting deepfake. IEEE Trans Inf Forensics Secur 18:2015\u20132029","journal-title":"IEEE Trans Inf Forensics Secur"},{"key":"18130_CR31","unstructured":"Knafo G, Fried O (2022) Fakeout: leveraging out-of-domain self-supervision for multi-modal video deepfake detection. arXiv preprint arXiv:2212.00773"},{"key":"18130_CR32","unstructured":"A. Business Insider. Deepfakes software for all. [Online]. Available: https:\/\/faceswap.dev\/. Available at https:\/\/github.com\/deepfakes\/faceswap"},{"key":"18130_CR33","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109628","volume":"141","author":"K Liu","year":"2023","unstructured":"Liu K, Perov I, Gao D, Chervoniy N, Zhou W, Zhang W (2023) Deep-facelab: integrated, flexible and extensible face-swapping framework. Pattern Recogn 141:109628","journal-title":"Pattern Recogn"},{"key":"18130_CR34","doi-asserted-by":"crossref","unstructured":"Nirkin Y, Keller Y, Hassner T (2019) Fsgan: subject agnostic face swapping and reenactment. In: Proceedings of the IEEE\/CVF international conference on computer vision, pp 7184\u20137193","DOI":"10.1109\/ICCV.2019.00728"},{"key":"18130_CR35","doi-asserted-by":"crossref","unstructured":"Thies J, Zollhofer M, Stamminger M, Theobalt C, Nie\u00dfner M (2016) Face2face: real-time face capture and reenactment of rgb videos. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 2387\u20132395","DOI":"10.1109\/CVPR.2016.262"},{"key":"18130_CR36","doi-asserted-by":"crossref","unstructured":"Mizuno K, Terachi Y, Takagi K, Izumi S, Kawaguchi H, Yoshimoto M (2012) Architectural study of hog feature extraction processor for real-time object detection. In: 2012 IEEE workshop on signal processing systems. IEEE, pp 197\u2013202","DOI":"10.1109\/SiPS.2012.57"},{"key":"18130_CR37","unstructured":"A. Communis (2021) Aurisaiai transcribe audio to text and add subtitles to videos instantly. [Online]. Available https:\/\/aurisai.io\/"},{"key":"18130_CR38","unstructured":"\u201cDlib python api tutorials link,\u201d 2015. Available from: http:\/\/dlib.net\/python\/index.html"},{"key":"18130_CR39","doi-asserted-by":"crossref","unstructured":"Fleet D, Weiss Y (2006) Optical flow estimation. In: Handbook of mathematical models in computer vision. Springer, pp 237\u2013257","DOI":"10.1007\/0-387-28831-7_15"},{"key":"18130_CR40","unstructured":"Simonyan K, Zisserman A (2014) Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556"},{"issue":"10","key":"18130_CR41","doi-asserted-by":"publisher","first-page":"2965","DOI":"10.1016\/j.patcog.2008.05.008","volume":"41","author":"D O\u2019Shaughnessy","year":"2008","unstructured":"O\u2019Shaughnessy D (2008) Automatic speech recognition: history, methods and challenges. Pattern Recogn 41(10):2965\u20132979","journal-title":"Pattern Recogn"},{"key":"18130_CR42","doi-asserted-by":"crossref","unstructured":"Chugh K, Gupta P, Dhall A, Subramanian R (2020) Not made for each other-audio-visual dissonance-based deepfake detection and localization. In: Proceedings of the 28th ACM International Conference on Multimedia, pp 439\u2013447","DOI":"10.1145\/3394171.3413700"},{"key":"18130_CR43","unstructured":"P. S. Foundation (2019) videocr 0.1.6-pypi. [Online]. Available: https:\/\/pypi.org\/project\/videocr\/"},{"key":"18130_CR44","volume-title":"Machine learning with PySpark: with natural language processing and recommender systems","author":"P Singh","year":"2018","unstructured":"Singh P (2018) Machine learning with PySpark: with natural language processing and recommender systems. Apress, Berkeley"},{"key":"18130_CR45","doi-asserted-by":"publisher","first-page":"151","DOI":"10.1007\/s11633-019-1211-x","volume":"17","author":"H Xu","year":"2020","unstructured":"Xu H, Ma Y, Liu H-C, Deb D, Liu H, Tang J-L, Jain AK (2020) Adversarial attacks and defenses in images, graphs and text: a review. Int J Autom Comput 17:151\u2013178","journal-title":"Int J Autom Comput"},{"issue":"03","key":"18130_CR46","first-page":"20","volume":"7","author":"V K\u00ebpuska","year":"2017","unstructured":"K\u00ebpuska V, Bohouta G (2017) Comparing speech recognition systems (microsoft api, google api and cmu sphinx). Int J Eng Res Appl 7(03):20\u201324","journal-title":"Int J Eng Res Appl"},{"key":"18130_CR47","doi-asserted-by":"crossref","unstructured":"Jin D, Jin Z, Zhou JT, Szolovits P (2020) Is bert really robust? A strong baseline for natural language attack on text classification and entailment. In: Proceedings of the AAAI conference on artificial intelligence, vol 34, no 05, pp 8018\u20138025","DOI":"10.1609\/aaai.v34i05.6311"},{"key":"18130_CR48","doi-asserted-by":"crossref","unstructured":"Szegedy C, Ioffe S, Vanhoucke V, Alemi AA (2017) Inception-v4, inception-resnet and the impact of residual connections on learning. In: Thirty-first AAAI conference on artificial intelligence","DOI":"10.1609\/aaai.v31i1.11231"},{"key":"18130_CR49","doi-asserted-by":"crossref","unstructured":"Huang G, Liu Z, Van Der Maaten L, Weinberger KQ (2017) Densely connected convolutional networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 4700\u20134708","DOI":"10.1109\/CVPR.2017.243"},{"key":"18130_CR50","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) Deep residual learning for image recognition. In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"18130_CR51","doi-asserted-by":"crossref","unstructured":"Khalid H, Kim M, Tariq S, Woo SS (2021) Evaluation of an audio-video multimodal deepfake dataset using unimodal and multimodal detectors. In: Proceedings of the 1st workshop on synthetic multimedia-audiovisual deepfake generation and detection, pp 7\u201315","DOI":"10.1145\/3476099.3484315"}],"container-title":["Multimedia Tools and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18130-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11042-024-18130-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11042-024-18130-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,7,22]],"date-time":"2024-07-22T01:19:29Z","timestamp":1721611169000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11042-024-18130-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,29]]},"references-count":51,"journal-issue":{"issue":"26","published-online":{"date-parts":[[2024,8]]}},"alternative-id":["18130"],"URL":"https:\/\/doi.org\/10.1007\/s11042-024-18130-1","relation":{},"ISSN":["1573-7721"],"issn-type":[{"value":"1573-7721","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,29]]},"assertion":[{"value":"12 December 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"24 October 2023","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 January 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}