{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,4]],"date-time":"2026-06-04T01:13:40Z","timestamp":1780535620344,"version":"3.54.1"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"11","license":[{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T00:00:00Z","timestamp":1744502400000},"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":["Vis Comput"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s00371-025-03886-w","type":"journal-article","created":{"date-parts":[[2025,4,13]],"date-time":"2025-04-13T14:00:18Z","timestamp":1744552818000},"page":"8579-8591","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Enhancing deepfake robustness via real discrete codebook reconstruction"],"prefix":"10.1007","volume":"41","author":[{"given":"Ping","family":"Chen","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ming","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Huanhuan","family":"Bao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lili","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,4,13]]},"reference":[{"key":"3886_CR1","doi-asserted-by":"publisher","first-page":"6821","DOI":"10.1109\/TMM.2022.3214776","volume":"25","author":"J Zhu","year":"2023","unstructured":"Zhu, J., Zhang, Q., Fei, L., Cai, R., Xie, Y., Sheng, B., Yang, X.: Fffn: Frame-by-frame feedback fusion network for video super-resolution. IEEE Trans. Multimed. 25, 6821\u20136835 (2023)","journal-title":"IEEE Trans. Multimed."},{"issue":"8","key":"3886_CR2","doi-asserted-by":"publisher","first-page":"4499","DOI":"10.1109\/TNNLS.2021.3116209","volume":"34","author":"Z Xie","year":"2023","unstructured":"Xie, Z., Zhang, W., Sheng, B., Li, P., Chen, C.L.P.: Bagfn: Broad attentive graph fusion network for high-order feature interactions. IEEE Trans. Neural Netw. Learn. Syst. 34(8), 4499\u20134513 (2023)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"1","key":"3886_CR3","doi-asserted-by":"publisher","first-page":"532","DOI":"10.1109\/TNNLS.2022.3175775","volume":"35","author":"A Karambakhsh","year":"2024","unstructured":"Karambakhsh, A., Sheng, B., Li, P., Li, H., Kim, J., Jung, Y., Chen, C.L.P.: Sparsevoxnet: 3-d object recognition with sparsely aggregation of 3-d dense blocks. IEEE Trans. Neural Netw. Learn. Syst. 35(1), 532\u2013546 (2024)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"3886_CR4","doi-asserted-by":"publisher","first-page":"289","DOI":"10.3390\/forensicsci4030021","volume":"4","author":"Z Akhtar","year":"2024","unstructured":"Akhtar, Z., Pendyala, T.L., Athmakuri, V.S.: Video and audio deepfake datasets and open issues in deepfake technology: being ahead of the curve. Forensic Sci. 4(3), 289\u2013377 (2024)","journal-title":"Forensic Sci."},{"key":"3886_CR5","doi-asserted-by":"crossref","unstructured":"Pham, L., Lam, P., Nguyen, T., Tang, H., Tran, D., Schindler, A., Zakaryan, T., Polonsky, A., Vu, C.: A comprehensive survey with critical analysis for deepfake speech detection. arXiv preprint arXiv:2409.15180 (2024)","DOI":"10.1016\/j.cosrev.2025.100757"},{"key":"3886_CR6","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.: Deepfacelab: Integrated, flexible and extensible face-swapping framework. Pattern Recognit. 141, 109628 (2023)","journal-title":"Pattern Recognit."},{"key":"3886_CR7","unstructured":"FaceSwap. https:\/\/github.com\/deepfakes\/faceswap Accessed 2024-01-24"},{"key":"3886_CR8","doi-asserted-by":"crossref","unstructured":"Li, Q., Wang, W., Xu, C., Sun, Z., Yang, M.-H.: Learning disentangled representation for one-shot progressive face swapping. IEEE IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TPAMI.2024.3404334"},{"issue":"12","key":"3886_CR9","doi-asserted-by":"publisher","first-page":"4217","DOI":"10.1109\/TPAMI.2020.2970919","volume":"43","author":"T Karras","year":"2021","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4217\u20134228 (2021)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3886_CR10","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8107\u20138116 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"issue":"1","key":"3886_CR11","doi-asserted-by":"publisher","first-page":"96","DOI":"10.1145\/3292039","volume":"62","author":"J Thies","year":"2018","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: Face2face: real-time face capture and reenactment of rgb videos. Commun. ACM 62(1), 96\u2013104 (2018)","journal-title":"Commun. ACM"},{"key":"3886_CR12","doi-asserted-by":"crossref","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGAN: Subject agnostic face swapping and reenactment. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 7184\u20137193 (2019)","DOI":"10.1109\/ICCV.2019.00728"},{"issue":"1","key":"3886_CR13","doi-asserted-by":"publisher","first-page":"560","DOI":"10.1109\/TPAMI.2022.3155571","volume":"45","author":"Y Nirkin","year":"2023","unstructured":"Nirkin, Y., Keller, Y., Hassner, T.: FSGANv2: Improved subject agnostic face swapping and reenactment. IEEE Trans. Pattern Anal. Mach. Intell. 45(1), 560\u2013575 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3886_CR14","doi-asserted-by":"crossref","unstructured":"Wang, S.-Y., Wang, O., Zhang, R., Owens, A., Efros, A.A.: Cnn-generated images are surprisingly easy to spot... for now. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.00872"},{"key":"3886_CR15","doi-asserted-by":"crossref","unstructured":"Wang, C., Deng, W.: Representative forgery mining for fake face detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 14923\u201314932 (2021)","DOI":"10.1109\/CVPR46437.2021.01468"},{"key":"3886_CR16","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1109\/TIFS.2022.3146781","volume":"17","author":"P Yu","year":"2022","unstructured":"Yu, P., Fei, J., Xia, Z., Zhou, Z., Weng, J.: Improving generalization by commonality learning in face forgery detection. IEEE Trans. Inf. Forensics Secur. 17, 547\u2013558 (2022)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"3886_CR17","doi-asserted-by":"crossref","unstructured":"Guarnera, L., Giudice, O., Battiato, S.: Deepfake detection by analyzing convolutional traces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops (2020)","DOI":"10.1109\/CVPRW50498.2020.00341"},{"key":"3886_CR18","doi-asserted-by":"crossref","unstructured":"Ru, Y., Zhou, W., Liu, Y., Sun, J., Li, Q.: Bita-net: Bi-temporal attention network for facial video forgery detection. In: 2021 IEEE International Joint Conference on Biometrics (IJCB), pp. 1\u20138 (2021). IEEE","DOI":"10.1109\/IJCB52358.2021.9484408"},{"key":"3886_CR19","doi-asserted-by":"crossref","unstructured":"Neekhara, P., Dolhansky, B., Bitton, J., Ferrer, C.C.: Adversarial threats to deepfake detection: A practical perspective. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 923\u2013932 (2021)","DOI":"10.1109\/CVPRW53098.2021.00103"},{"key":"3886_CR20","doi-asserted-by":"publisher","first-page":"24","DOI":"10.1016\/j.vrih.2022.06.001","volume":"5","author":"W Shao","year":"2023","unstructured":"Shao, W., Rajapaksha, P., Wei, Y., Li, D., Crespi, N., Luo, Z.-Q.T.: Covad: Content-oriented video anomaly detection using a self-attention based deep learning model. Virtual Real. Intell. Hardw. 5, 24\u201341 (2023)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"3886_CR21","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1109\/TMM.2021.3120873","volume":"25","author":"X Lin","year":"2021","unstructured":"Lin, X., Sun, S., Huang, W., Sheng, B., Li, P., Feng, D.D.: Eapt: Efficient attention pyramid transformer for image processing. IEEE Trans. Multimed. 25, 50\u201361 (2021)","journal-title":"IEEE Trans. Multimed."},{"key":"3886_CR22","doi-asserted-by":"publisher","first-page":"57","DOI":"10.1016\/j.vrih.2022.07.006","volume":"5","author":"M Zhang","year":"2023","unstructured":"Zhang, M., Tian, X.: A transformer architecture based mutual attention for image anomaly detection. Virtual Real. Intell. Hardw. 5, 57\u201367 (2023)","journal-title":"Virtual Real. Intell. Hardw."},{"key":"3886_CR23","doi-asserted-by":"publisher","first-page":"6662","DOI":"10.1109\/TCYB.2021.3079311","volume":"52","author":"B Sheng","year":"2021","unstructured":"Sheng, B., Li, P., Ali, R., Chen, C.L.P.: Improving video temporal consistency via broad learning system. IEEE Trans. Cybern. 52, 6662\u20136675 (2021)","journal-title":"IEEE Trans. Cybern."},{"key":"3886_CR24","doi-asserted-by":"crossref","unstructured":"R\u00f6ssler, A., Cozzolino, D., Verdoliva, L., Riess, C., Thies, J., Nie\u00dfner, M.: FaceForensics++: Learning to detect manipulated facial images. In: International Conference on Computer Vision (ICCV) (2019)","DOI":"10.1109\/ICCV.2019.00009"},{"key":"3886_CR25","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"3886_CR26","doi-asserted-by":"crossref","unstructured":"Haliassos, A., Vougioukas, K., Petridis, S., Pantic, M.: Lips don\u2019t lie: A generalisable and robust approach to face forgery detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5039\u20135049 (2021)","DOI":"10.1109\/CVPR46437.2021.00500"},{"key":"3886_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, H., Zhou, W., Chen, D., Wei, T., Zhang, W., Yu, N.: Multi-attentional deepfake detection. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 2185\u20132194 (2021)","DOI":"10.1109\/CVPR46437.2021.00222"},{"key":"3886_CR28","unstructured":"Tan, M., Le, Q.: EfficientNet: Rethinking model scaling for convolutional neural networks. In: Chaudhuri, K., Salakhutdinov, R. (eds.) Proceedings of the 36th International Conference on Machine Learning. Proceedings of Machine Learning Research, vol. 97, pp. 6105\u20136114. PMLR, (2019)"},{"key":"3886_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, D., Lin, F., Hua, Y., Wang, P., Zeng, D., Ge, S.: Deepfake video detection with spatiotemporal dropout transformer. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 5833\u20135841 (2022)","DOI":"10.1145\/3503161.3547913"},{"key":"3886_CR30","unstructured":"Dosovitskiy, A., Beyer, L., Kolesnikov, A., Weissenborn, D., Zhai, X., Unterthiner, T., Dehghani, M., Minderer, M., Heigold, G., Gelly, S., Uszkoreit, J., Houlsby, N.: An image is worth 16x16 words: Transformers for image recognition at scale. CoRR arXiv:2010.11929 (2020)"},{"key":"3886_CR31","first-page":"219","volume-title":"Image Analysis and Processing - ICIAP 2022","author":"DA Coccomini","year":"2022","unstructured":"Coccomini, D.A., Messina, N., Gennaro, C., Falchi, F.: Combining efficientnet and vision transformers for video deepfake detection. In: Sclaroff, S., Distante, C., Leo, M., Farinella, G.M., Tombari, F. (eds.) Image Analysis and Processing - ICIAP 2022, pp. 219\u2013229. Springer, Cham (2022)"},{"key":"3886_CR32","unstructured":"Tan, M., Le, Q.: Efficientnet: Rethinking model scaling for convolutional neural networks. In: International Conference on Machine Learning, pp. 6105\u20136114 (2019). PMLR"},{"key":"3886_CR33","doi-asserted-by":"crossref","unstructured":"Lin, H., Huang, W., Luo, W., Lu, W.: Deepfake detection with multi-scale convolution and vision transformer. Digit. Signal Process. 134(C) (2023)","DOI":"10.1016\/j.dsp.2022.103895"},{"key":"3886_CR34","doi-asserted-by":"crossref","unstructured":"Sekar, R., Rajkumar, D., Anne, K.: Deep fake detection using an optimal deep learning model with multi head attention-based feature extraction scheme. The Visual Computer, 1\u201318 (2024)","DOI":"10.1007\/s00371-024-03567-0"},{"key":"3886_CR35","doi-asserted-by":"crossref","unstructured":"Fahad, M., Zhang, T., Iqbal, Y., Ikram, A., Siddiqui, F., Abdullah, B., Nauman, M., Zhao, X., Geng, Y.: Advanced deepfake detection with enhanced resnet-18 and multilayer cnn max pooling. The Visual Computer, 1\u201314 (2024)","DOI":"10.1007\/s00371-024-03613-x"},{"key":"3886_CR36","doi-asserted-by":"crossref","unstructured":"Gandhi, A., Jain, S.: Adversarial perturbations fool deepfake detectors. In: 2020 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20138 (2020)","DOI":"10.1109\/IJCNN48605.2020.9207034"},{"key":"3886_CR37","unstructured":"Goodfellow, I.J., Shlens, J., Szegedy, C.: Explaining and harnessing adversarial examples. In: 3rd International Conference on Learning Representations, ICLR 2015, San Diego, CA, USA, May 7-9, 2015, Conference Track Proceedings (2015)"},{"key":"3886_CR38","doi-asserted-by":"crossref","unstructured":"Carlini, N., Wagner, D.: Adversarial examples are not easily detected: Bypassing ten detection methods. In: Proceedings of the 10th ACM Workshop on Artificial Intelligence and Security, pp. 3\u201314 (2017)","DOI":"10.1145\/3128572.3140444"},{"key":"3886_CR39","doi-asserted-by":"crossref","unstructured":"Hussain, S., Neekhara, P., Jere, M., Koushanfar, F., McAuley, J.: Adversarial deepfakes: Evaluating vulnerability of deepfake detectors to adversarial examples. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 3348\u20133357 (2021)","DOI":"10.1109\/WACV48630.2021.00339"},{"key":"3886_CR40","doi-asserted-by":"crossref","unstructured":"Li, D., Wang, W., Fan, H., Dong, J.: Exploring adversarial fake images on face manifold. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 5789\u20135798 (2021)","DOI":"10.1109\/CVPR46437.2021.00573"},{"key":"3886_CR41","doi-asserted-by":"crossref","unstructured":"Fan, L., Li, W., Cui, X.: Deepfake-image anti-forensics with adversarial examples attacks. Future Internet 13(11) (2021)","DOI":"10.3390\/fi13110288"},{"key":"3886_CR42","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et al.: Neural discrete representation learning. Advances in neural information processing systems 30 (2017)"},{"key":"3886_CR43","unstructured":"Razavi, A., Oord, A., Vinyals, O.: Generating diverse high-fidelity images with vq-vae-2. Advances in neural information processing systems 32 (2019)"},{"key":"3886_CR44","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"3886_CR45","doi-asserted-by":"crossref","unstructured":"Selvaraju, R.R., Cogswell, M., Das, A., Vedantam, R., Parikh, D., Batra, D.: Grad-cam: Visual explanations from deep networks via gradient-based localization. In: 2017 IEEE International Conference on Computer Vision (ICCV), pp. 618\u2013626 (2017)","DOI":"10.1109\/ICCV.2017.74"},{"key":"3886_CR46","doi-asserted-by":"crossref","unstructured":"Li, Y., Yang, X., Sun, P., Qi, H., Lyu, S.: Celeb-df: A large-scale challenging dataset for deepfake forensics. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 3204\u20133213 (2020)","DOI":"10.1109\/CVPR42600.2020.00327"},{"key":"3886_CR47","doi-asserted-by":"crossref","unstructured":"Kurakin, A., Goodfellow, I., Bengio, S., Dong, Y., Liao, F., Liang, M., Pang, T., Zhu, J., Hu, X., Xie, C., Wang, J., Zhang, Z., Ren, Z., Yuille, A., Huang, S., Zhao, Y., Zhao, Y., Han, Z., Long, J., Berdibekov, Y., Akiba, T., Tokui, S., Abe, M.: Adversarial attacks and defences competition. In: Escalera, S., Weimer, M. (eds.) The NIPS \u201917 Competition: Building Intelligent Systems, pp. 195\u2013231 (2018)","DOI":"10.1007\/978-3-319-94042-7_11"},{"key":"3886_CR48","unstructured":"Sriramanan, G., Addepalli, S., Baburaj, A., R, V.B.: Guided adversarial attack for evaluating and enhancing adversarial defenses. In: Larochelle, H., Ranzato, M., Hadsell, R., Balcan, M.F., Lin, H. (eds.) Advances in Neural Information Processing Systems, vol. 33, pp. 20297\u201320308 (2020)"},{"key":"3886_CR49","unstructured":"Kim, H.: Torchattacks: A pytorch repository for adversarial attacks. arXiv preprint arXiv:2010.01950 (2020)"}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03886-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00371-025-03886-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-025-03886-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,6]],"date-time":"2025-09-06T11:01:32Z","timestamp":1757156492000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00371-025-03886-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,4,13]]},"references-count":49,"journal-issue":{"issue":"11","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["3886"],"URL":"https:\/\/doi.org\/10.1007\/s00371-025-03886-w","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,4,13]]},"assertion":[{"value":"11 March 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 April 2025","order":2,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors have no conflict of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}},{"value":"Not applicable.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and informed consent for data used"}}]}}