{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,11]],"date-time":"2026-02-11T01:43:31Z","timestamp":1770774211841,"version":"3.50.0"},"reference-count":50,"publisher":"Wiley","license":[{"start":{"date-parts":[[2021,8,2]],"date-time":"2021-08-02T00:00:00Z","timestamp":1627862400000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key R&D Program Special Fund","award":["2018YFC1505805"],"award-info":[{"award-number":["2018YFC1505805"]}]},{"name":"National Key R&D Program Special Fund","award":["62072106"],"award-info":[{"award-number":["62072106"]}]},{"name":"National Key R&D Program Special Fund","award":["61070062"],"award-info":[{"award-number":["61070062"]}]},{"name":"National Key R&D Program Special Fund","award":["2020J01168"],"award-info":[{"award-number":["2020J01168"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2018YFC1505805"],"award-info":[{"award-number":["2018YFC1505805"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62072106"],"award-info":[{"award-number":["62072106"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61070062"],"award-info":[{"award-number":["61070062"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2020J01168"],"award-info":[{"award-number":["2020J01168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2018YFC1505805"],"award-info":[{"award-number":["2018YFC1505805"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["62072106"],"award-info":[{"award-number":["62072106"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["61070062"],"award-info":[{"award-number":["61070062"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2020J01168"],"award-info":[{"award-number":["2020J01168"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Security and Communication Networks"],"published-print":{"date-parts":[[2021,8,2]]},"abstract":"<jats:p>Facial manipulation enables facial expressions to be tampered with or facial identities to be replaced in videos. The fake videos are so realistic that they are even difficult for human eyes to distinguish. This poses a great threat to social and public information security. A number of facial manipulation detectors have been proposed to address this threat. However, previous studies have shown that the accuracy of these detectors is sensitive to adversarial examples. The existing defense methods are very limited in terms of applicable scenes and defense effects. This paper proposes a new defense strategy for facial manipulation detectors, which combines a passive defense method, bilateral filtering, and a proactive defense method, joint adversarial training, to mitigate the vulnerability of facial manipulation detectors against adversarial examples. The bilateral filtering method is applied in the preprocessing stage of the model without any modification to denoise the input adversarial examples. The joint adversarial training starts from the training stage of the model, which mixes various adversarial examples and original examples to train the model. The introduction of joint adversarial training can train a model that defends against multiple adversarial attacks. The experimental results show that the proposed defense strategy positively helps facial manipulation detectors counter adversarial examples.<\/jats:p>","DOI":"10.1155\/2021\/4280328","type":"journal-article","created":{"date-parts":[[2021,8,3]],"date-time":"2021-08-03T22:35:09Z","timestamp":1628030109000},"page":"1-10","source":"Crossref","is-referenced-by-count":7,"title":["A Novel Defensive Strategy for Facial Manipulation Detection Combining Bilateral Filtering and Joint Adversarial Training"],"prefix":"10.1155","volume":"2021","author":[{"given":"Yifan","family":"Luo","sequence":"first","affiliation":[{"name":"College of Mathematics and Informatics, Fujian Normal University, Fuzhou 350117, China"},{"name":"Digital Fujian Institute of Big Data Security Technology, Fuzhou 350117, China"}]},{"given":"Feng","family":"Ye","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, Fujian Normal University, Fuzhou 350117, China"},{"name":"Digital Fujian Institute of Big Data Security Technology, Fuzhou 350117, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1291-0154","authenticated-orcid":true,"given":"Bin","family":"Weng","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, Fujian Normal University, Fuzhou 350117, China"},{"name":"Digital Fujian Institute of Big Data Security Technology, Fuzhou 350117, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2281-5150","authenticated-orcid":true,"given":"Shan","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Mathematics, Physics and Statistics, The University of British Columbia, Vancouver, Okanagan, Canada"}]},{"given":"Tianqiang","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Mathematics and Informatics, Fujian Normal University, Fuzhou 350117, China"},{"name":"Digital Fujian Institute of Big Data Security Technology, Fuzhou 350117, China"}]}],"member":"311","reference":[{"key":"1","article-title":"You won\u2019t believe what Obama says in this video!","author":"Buzz Feed Video","year":"2018"},{"key":"2","article-title":"Jennifer Lawrence-Buscemi on her favorite housewives [Deepfake]","author":"Birb Fakes","year":"2019"},{"key":"3","article-title":"Leveraging frequency analysis for deep fake image recognition","author":"J. Frank","year":"2020"},{"key":"4","article-title":"Detection of deep network generated images using disparities in color components","author":"H. Li","year":"2018"},{"key":"5","first-page":"6","article-title":"DeepFake video production and SIFT-based analysis","author":"M. \u0110or\u0111evi\u0107"},{"issue":"7","key":"6","doi-asserted-by":"crossref","first-page":"3286","DOI":"10.1109\/TIP.2019.2895466","article-title":"Hybrid LSTM and encoder\u2013decoder architecture for detection of image forgeries","volume":"28","author":"J. H. Bappy","year":"2019","journal-title":"IEEE Transactions on Image Processing"},{"key":"7","doi-asserted-by":"publisher","DOI":"10.1109\/WIFS.2018.8630761"},{"key":"8","doi-asserted-by":"publisher","DOI":"10.1109\/AVSS.2018.8639163"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.23919\/CCC50068.2020.9189596"},{"key":"10","article-title":"Use of a capsule network to detect fake images and videos","author":"H. H. Nguyen","year":"2019"},{"key":"11","doi-asserted-by":"crossref","DOI":"10.1109\/IJCNN48605.2020.9207034","article-title":"Adversarial perturbations fool Deepfake detectors","author":"A. Gandhi","year":"2020"},{"key":"12","article-title":"Adversarial Deepfakes: evaluating vulnerability of Deepfake detectors to adversarial examples","author":"P. Neekhara","year":"2020"},{"key":"13","doi-asserted-by":"crossref","DOI":"10.1109\/CVPRW50498.2020.00337","article-title":"Evading Deepfake-image detectors with white-and black-box Attacks","author":"N. Carlini","year":"2020"},{"key":"14","article-title":"CNN-generated images are surprisingly easy to spot\u2026 for now","author":"S.-Y. Wang","year":"2019"},{"key":"15","article-title":"Explaining and harnessing adversarial examples","author":"I. J. Goodfellow","year":"2014"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.49"},{"key":"17","article-title":"Deep residual learning for image recognition","author":"K. He","year":"2015"},{"key":"18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"K. Simonyan","year":"2014"},{"key":"19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"20","article-title":"Adversarial examples in the physical world","author":"A. Kurakin","year":"2016"},{"key":"21","article-title":"Towards deep learning models resistant to adversarial attacks","author":"A. Madry","year":"2017"},{"key":"22","article-title":"Fast is better than free: revisiting adversarial training","author":"E. Wong","year":"2020"},{"key":"23","article-title":"DeepFakes","author":"Deepfakes","year":"2020"},{"key":"24","article-title":"FaceSwap","author":"M. Kowalski","year":"2021"},{"key":"25","doi-asserted-by":"crossref","DOI":"10.1109\/ICCV.2019.00728","article-title":"FSGAN: subject agnostic face swapping and reenactment","author":"Y. Nirkin","year":"2019"},{"key":"26","article-title":"FaceShifter: towards high fidelity and occlusion aware face swapping","author":"L. Li","year":"2019"},{"key":"27","article-title":"Unsupervised image-to-image translation networks","author":"M.-Y. Liu","year":"2017"},{"key":"28","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818056"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.262"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1145\/3306346.3323035"},{"key":"31","article-title":"In Ictu Oculi: exposing AI generated fake face videos by detecting eye blinking","author":"Y. Li","year":"2018"},{"key":"32","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683164"},{"key":"33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00152"},{"key":"34","article-title":"Unmasking DeepFakes with simple features","author":"R. Durall","year":"2019"},{"key":"35","article-title":"Exposing DeepFake videos by detecting face warping artifacts","author":"Y. Li","year":"2018"},{"key":"36","article-title":"Dynamic routing between capsules","author":"S. Sabour","year":"2017"},{"key":"37","article-title":"FaceForensics++: learning to detect manipulated facial images","author":"A. R\u00f6ssler","year":"2019"},{"key":"38","article-title":"Face forgery detection by 3D decomposition","author":"X. Zhu","year":"2020"},{"key":"39","article-title":"Sharp multiple instance learning for DeepFake video detection","author":"X. Li","year":"2020"},{"key":"40","article-title":"Mining generalized features for detecting AI-manipulated fake faces","author":"Y. Yu","year":"2020"},{"key":"41","article-title":"Spatio-temporal features for generalized detection of Deepfake videos","author":"I. Ganiyusufoglu","year":"2020"},{"key":"42","article-title":"Frequency-aware discriminative feature learning supervised by single-center loss for face forgery detection","author":"J. Li","year":"2021"},{"key":"43","article-title":"Multi-attentional Deepfake detection","author":"H. Zhao","year":"2021"},{"key":"44","article-title":"DeepFake detection based on the discrepancy between the face and its context","author":"Y. Nirkin","year":"2021"},{"key":"45","article-title":"Intriguing properties of neural networks","author":"C. Szegedy","year":"2013"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.1145\/3097983.3098158"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2016.41"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.1109\/CISS.2018.8362326"},{"key":"49","doi-asserted-by":"crossref","DOI":"10.1038\/s42256-019-0104-6","article-title":"Adversarial explanations for understanding image classification decisions and improved neural network robustness","author":"W. Woods","year":"2019"},{"key":"50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00984"}],"container-title":["Security and Communication Networks"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/4280328.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/4280328.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/scn\/2021\/4280328.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,1,6]],"date-time":"2023-01-06T11:31:44Z","timestamp":1673004704000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/scn\/2021\/4280328\/"}},"subtitle":[],"editor":[{"given":"Zhili","family":"Zhou","sequence":"additional","affiliation":[]}],"short-title":[],"issued":{"date-parts":[[2021,8,2]]},"references-count":50,"alternative-id":["4280328","4280328"],"URL":"https:\/\/doi.org\/10.1155\/2021\/4280328","relation":{},"ISSN":["1939-0122","1939-0114"],"issn-type":[{"value":"1939-0122","type":"electronic"},{"value":"1939-0114","type":"print"}],"subject":[],"published":{"date-parts":[[2021,8,2]]}}}