{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:43:51Z","timestamp":1775771031957,"version":"3.50.1"},"reference-count":35,"publisher":"MDPI AG","issue":"5","license":[{"start":{"date-parts":[[2023,5,17]],"date-time":"2023-05-17T00:00:00Z","timestamp":1684281600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"National Key Research and Development Program of China","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"National Key Research and Development Program of China","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"National Key Research and Development Program of China","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"National Key Research and Development Program of China","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"National Key Research and Development Program of China","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"National Key Research and Development Program of China","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]},{"name":"National Natural Science Foundation of China","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"National Natural Science Foundation of China","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"National Natural Science Foundation of China","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"National Natural Science Foundation of China","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"National Natural Science Foundation of China","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"National Natural Science Foundation of China","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"National Natural Science Foundation of China","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"Guizhou Province Science and Technology Plan Project","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"Research Project of Guizhou University for Talent Introduction","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]},{"name":"Cultivation Project of Guizhou University","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"Cultivation Project of Guizhou University","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"Cultivation Project of Guizhou University","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"Cultivation Project of Guizhou University","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"Cultivation Project of Guizhou University","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"Cultivation Project of Guizhou University","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"Cultivation Project of Guizhou University","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"Open Fund of Key Laboratory of Advanced Manufacturing Technology, Ministry of Education","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["2022YFB2701401"],"award-info":[{"award-number":["2022YFB2701401"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["62272124"],"award-info":[{"award-number":["62272124"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["Qiankehe platform talent [2020]5017"],"award-info":[{"award-number":["Qiankehe platform talent [2020]5017"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["[2020]61"],"award-info":[{"award-number":["[2020]61"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["[2019]56"],"award-info":[{"award-number":["[2019]56"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["GZUAMT2021KF[01]"],"award-info":[{"award-number":["GZUAMT2021KF[01]"]}]},{"name":"Young Science and Technology Talent Growth Program of Department of Education of Guizhou Province","award":["Guizhou-Education-Contact-KY [2018]141"],"award-info":[{"award-number":["Guizhou-Education-Contact-KY [2018]141"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Entropy"],"abstract":"<jats:p>Federated learning protects the privacy information in the data set by sharing the average gradient. However, \u201cDeep Leakage from Gradient\u201d (DLG) algorithm as a gradient-based feature reconstruction attack can recover privacy training data using gradients shared in federated learning, resulting in private information leakage. However, the algorithm has the disadvantages of slow model convergence and poor inverse generated images accuracy. To address these issues, a Wasserstein distance-based DLG method is proposed, named WDLG. The WDLG method uses Wasserstein distance as the training loss function achieved to improve the inverse image quality and the model convergence. The hard-to-calculate Wasserstein distance is converted to be calculated iteratively using the Lipschit condition and Kantorovich\u2013Rubinstein duality. Theoretical analysis proves the differentiability and continuity of Wasserstein distance. Finally, experiment results show that the WDLG algorithm is superior to DLG in training speed and inversion image quality. At the same time, we prove through the experiments that differential privacy can be used for disturbance protection, which provides some ideas for the development of a deep learning framework to protect privacy.<\/jats:p>","DOI":"10.3390\/e25050810","type":"journal-article","created":{"date-parts":[[2023,5,18]],"date-time":"2023-05-18T07:35:50Z","timestamp":1684395350000},"page":"810","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Wasserstein Distance-Based Deep Leakage from Gradients"],"prefix":"10.3390","volume":"25","author":[{"given":"Zifan","family":"Wang","sequence":"first","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8733-4596","authenticated-orcid":false,"given":"Changgen","family":"Peng","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"Guizhou Big Data Academy, Guizhou University, Guiyang 550025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xing","family":"He","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"Academic Affairs Office of Guizhou University for Nationalities, Guizhou Minzu University, Guiyang 550025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6590-5757","authenticated-orcid":false,"given":"Weijie","family":"Tan","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Public Big Data, College of Computer Science and Technology, Guizhou University, Guiyang 550025, China"},{"name":"Key Laboratory of Advanced Manufacturing Technology, Ministry of Education, Guizhou University, Guiyang 550025, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2023,5,17]]},"reference":[{"key":"ref_1","unstructured":"Kone\u010dn\u00fd, J., McMahan, H.B., Ramage, D., and Richt\u00e1rik, P. (2016). Federated optimization: Distributed machine learning for on-device intelligence. arXiv."},{"key":"ref_2","unstructured":"McMahan, H.B., Moore, E., Ramage, D., and Arcas, B.A.Y. (2016). Federated learning of deep networks using model averaging. arXiv."},{"key":"ref_3","doi-asserted-by":"crossref","unstructured":"Iandola, F.N., Moskewicz, M.W., Ashraf, K., and Keutzer, K. (2016). FireCaffe: Near-Linear Acceleration of Deep Neural Network Training on Compute Clusters. arXiv.","DOI":"10.1109\/CVPR.2016.284"},{"key":"ref_4","doi-asserted-by":"crossref","unstructured":"Li, M., Andersen, D.G., Park, J.W., Smola, A.J., Ahmed, A., Josifovski, V., and Su, B.Y. (2014, January 4\u20137). Scaling distributed machine learning with the parameter server. Proceedings of the 2014 International Conference on Big Data Science and Computing, Beijing, China.","DOI":"10.1145\/2640087.2644155"},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"84","DOI":"10.1145\/3065386","article-title":"Imagenet classification with deep convolutional neural networks","volume":"60","author":"Krizhevsky","year":"2017","journal-title":"Commun. ACM"},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"344","DOI":"10.1016\/j.ijrobp.2017.04.021","article-title":"Developing and validating a survival prediction model for NSCLC patients through distributed learning across 3 countries","volume":"99","author":"Jochems","year":"2017","journal-title":"Int. J. Radiat. Oncol. Biol. Phys."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"459","DOI":"10.1016\/j.radonc.2016.10.002","article-title":"Distributed learning: Developing a predictive model based on data from multiple hospitals without data leaving the hospital-A real life proof of concept","volume":"121","author":"Jochems","year":"2016","journal-title":"Radiother. Oncol."},{"key":"ref_8","unstructured":"Zhu, L., Liu, Z., and Han, S. (2019, January 8\u201314). Deep leakage from gradients. Proceedings of the 33rd International Conference on Neural Information Processing Systems, Vancouver, BC, Canada."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"405","DOI":"10.1146\/annurev-statistics-030718-104938","article-title":"Statistical aspects of Wasserstein distances","volume":"6","author":"Panaretos","year":"2019","journal-title":"Annu. Rev. Stat. Its Appl."},{"key":"ref_10","unstructured":"Iandola, F. (2016). Exploring the Design Space of Deep Convolutional Neural Networks at Large Scale, University of California, Berkeley."},{"key":"ref_11","unstructured":"Kim, H., Park, J., Jang, J., and Yoon, S. (2016). Deepspark: Spark-based deep learning supporting asynchronous updates and caffe compatibility. arXiv."},{"key":"ref_12","unstructured":"Sergeev, A., and Del Balso, M. (2018). Horovod: Fast and easy distributed deep learning in TensorFlow. arXiv."},{"key":"ref_13","unstructured":"Jia, X., Song, S., He, W., Wang, Y., Rong, H., Zhou, F., and Chu, X. (2018). Highly scalable deep learning training system with mixed-precision: Training imagenet in four minutes. arXiv."},{"key":"ref_14","unstructured":"You, Y., Gitman, I., and Ginsburg, B. (2017). Scaling sgd batch size to 32k for imagenet training. arXiv."},{"key":"ref_15","unstructured":"Recht, B., Re, C., Wright, S., and Niu, F. (2011, January 12\u201315). Hogwild!: A lock-free approach to parallelizing stochastic gradient descent. Proceedings of the 24th International Conference on Neural Information Processing Systems, Granada, Spain."},{"key":"ref_16","unstructured":"Paszke, A., Gross, S., Chintala, S., Chanan, G., Yang, E., DeVito, Z., and Lerer, A. (2017, January 28). Automatic differentiation in pytorch. Proceedings of the NIPS 2017 Autodiff Workshop, Long Beach, CA, USA."},{"key":"ref_17","doi-asserted-by":"crossref","unstructured":"Ketkar, N., and Moolayil, J. (2021). Deep Learning with Python: Learn Best Practices of Deep Learning Models with PyTorch, Apress.","DOI":"10.1007\/978-1-4842-5364-9"},{"key":"ref_18","unstructured":"Subramanian, V. (2018). Deep Learning with PyTorch: A Practical Approach to Building Neural Network Models Using PyTorch, Packt Publishing Ltd."},{"key":"ref_19","unstructured":"McMahan, B., Moore, E., Ramage, D., Hampson, S., and y Arcas, B.A. (2017, January 20\u201322). Communication-efficient learning of deep networks from decentralized data. Proceedings of the Artificial intelligence and statistics PMLR, Fort Lauderdale, FL, USA."},{"key":"ref_20","unstructured":"Kone\u010dn\u00fd, J., McMahan, H.B., Yu, F.X., Richt\u00e1rik, P., Suresh, A.T., and Bacon, D. (2016). Federated learning: Strategies for improving communication efficiency. arXiv."},{"key":"ref_21","doi-asserted-by":"crossref","unstructured":"Melis, L., Song, C., De Cristofaro, E., and Shmatikov, V. (2019, January 16). Exploiting unintended feature leakage in collaborative learning. Proceedings of the 2019 IEEE Symposium on Security and Privacy (SP), San Francisco, CA, USA.","DOI":"10.1109\/SP.2019.00029"},{"key":"ref_22","doi-asserted-by":"crossref","unstructured":"Fredrikson, M., Jha, S., and Ristenpart, T. (2015, January 12\u201316). Model inversion attacks that exploit confidence information and basic countermeasures. Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security, Denver, CO, USA.","DOI":"10.1145\/2810103.2813677"},{"key":"ref_23","doi-asserted-by":"crossref","unstructured":"Shokri, R., Stronati, M., Song, C., and Shmatikov, V. (2017, January 22\u201326). Membership inference attacks against machine learning models. Proceedings of the 2017 IEEE Symposium on Security and Privacy (SP), San Jose, CA, USA.","DOI":"10.1109\/SP.2017.41"},{"key":"ref_24","doi-asserted-by":"crossref","unstructured":"Wang, Z., Song, M., Zhang, Z., Song, Y., Wang, Q., and Qi, H. (May, January 29). Beyond inferring class representatives: User-level privacy leakage from federated learning. Proceedings of the IEEE INFOCOM 2019-IEEE Conference on Computer Communications, Paris, France.","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"2430","DOI":"10.1109\/JSAC.2020.3000372","article-title":"Analyzing user-level privacy attack against federated learning","volume":"38","author":"Song","year":"2020","journal-title":"IEEE J. Sel. Areas Commun."},{"key":"ref_26","unstructured":"Ghoussoub, N. (2017). Optimal ballistic transport and Hopf-Lax formulae on Wasserstein space. arXiv."},{"key":"ref_27","unstructured":"Arjovsky, M., and Chintala, S. (2017). Leon Bottou, Wasserstein gan. arXiv."},{"key":"ref_28","unstructured":"Geiping, J., Bauermeister, H., Drge, H., and Moeller, M. (2020). Inverting gradients-how easy is it to break privacy in federated learning?. arXiv."},{"key":"ref_29","unstructured":"Zhao, B., Mopuri, K.R., and Bilen, H. (2020). idlg: Improved deep leakage from gradients. arXiv."},{"key":"ref_30","unstructured":"Wei, W., Liu, L., Loper, M., Chow, K.-H., Gursoy, M.E., Truex, S., and Wu, Y. (2020). A framework for evaluating gradient leakage attacks in federated learning. arXiv."},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Haroush, M., Hubara, I., Hoffer, E., and Soudry, D. (2020, January 13\u201319). The knowledge within: Methods for data-free model compression. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00852"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Cai, Y., Yao, Z., Dong, Z., Gholami, A., Mahoney, M.W., and Keutzer, K. (2020, January 13\u201319). Zeroq: A novel zero shot quantization framework. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.01318"},{"key":"ref_33","doi-asserted-by":"crossref","unstructured":"Yin, H., Molchanov, P., Alvarez, J.M., Li, Z., Mallya, A., Hoiem, D., and Kautz, J. (2020, January 13\u201319). Dreaming to distill: Data-free knowledge transfer via deepinversion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Seattle, WA, USA.","DOI":"10.1109\/CVPR42600.2020.00874"},{"key":"ref_34","doi-asserted-by":"crossref","unstructured":"Yin, H., Mallya, A., Vahdat, A., Alvarez, J.M., Kautz, J., and Molchanov, P. (2021, January 20\u201325). See through gradients: Image batch recovery via gradinversion. Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, Nashville, TN, USA.","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"ref_35","doi-asserted-by":"crossref","unstructured":"Abadi, M., Chu, A., Goodfellow, I., Goodfellow, I., McMahan, H.B., Mironov, I., Talwar, K., and Zhang, L. (2016, January 24\u201328). Deep learning with differential privacy. Proceedings of the 2016 ACM SIGSAC Conference on Computer and Communications Security, Vienna, Austria.","DOI":"10.1145\/2976749.2978318"}],"container-title":["Entropy"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/5\/810\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,10]],"date-time":"2025-10-10T19:37:08Z","timestamp":1760125028000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1099-4300\/25\/5\/810"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,5,17]]},"references-count":35,"journal-issue":{"issue":"5","published-online":{"date-parts":[[2023,5]]}},"alternative-id":["e25050810"],"URL":"https:\/\/doi.org\/10.3390\/e25050810","relation":{},"ISSN":["1099-4300"],"issn-type":[{"value":"1099-4300","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,5,17]]}}}