{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:40:15Z","timestamp":1758980415644,"version":"3.44.0"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"14","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Key R&D Program of China under Grant number","award":["2022YFB3103100"],"award-info":[{"award-number":["2022YFB3103100"]}]},{"name":"R&D Program of the Beijing Municipal Education Commission","award":["KM202210005028"],"award-info":[{"award-number":["KM202210005028"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92167102","62302020"],"award-info":[{"award-number":["92167102","62302020"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Appl Intell"],"published-print":{"date-parts":[[2025,9]]},"DOI":"10.1007\/s10489-025-06533-y","type":"journal-article","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T12:44:30Z","timestamp":1757421870000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A gradient inversion attack defense method based on data augmentation"],"prefix":"10.1007","volume":"55","author":[{"given":"Yingge","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0000-1523-6196","authenticated-orcid":false,"given":"Xianlin","family":"Wu","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6414-9697","authenticated-orcid":false,"given":"Yuwen","family":"Chen","sequence":"additional","affiliation":[]},{"given":"Haiyang","family":"Yu","sequence":"additional","affiliation":[]},{"given":"Zhen","family":"Yang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,9]]},"reference":[{"key":"6533_CR1","doi-asserted-by":"crossref","unstructured":"Shokri R, Shmatikov V (2015) \u201cPrivacy-Preserving Deep Learning,\u201d In: Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security - CCS \u201915. ACM Press, pp 1310\u20131321","DOI":"10.1145\/2810103.2813687"},{"key":"6533_CR2","unstructured":"McMahan B, Moore E, Ramage D, Hampson S, y\u00a0Arcas B\u00a0A (2017) \u201cCommunication-Efficient Learning of Deep Networks from Decentralized Data,\u201d In: Artificial Intelligence and Statistics. PMLR, pp 1273\u20131282"},{"key":"6533_CR3","doi-asserted-by":"crossref","unstructured":"Kairouz P, McMahan H\u00a0B, Avent B, Bellet A, Bennis M, Bhagoji A\u00a0N, Bonawitz K, Charles Z, Cormode G, Cummings R, et\u00a0al. (2021) \u201cAdvances and open problems in federated learning,\u201d Found Trends\u00ae Mach Learn, vol\u00a014, no 1\u20132, pp 1\u2013210","DOI":"10.1561\/2200000083"},{"key":"6533_CR4","unstructured":"Zhu L, Liu Z, Han S (2019) \u201cDeep leakage from gradients,\u201d In: Advances in Neural Information Processing Systems, vol\u00a032. Curran Associates, Inc.,"},{"key":"6533_CR5","unstructured":"Zhao B, Mopuri K\u00a0R, Bilen H. \u201ciDLG: Improved Deep Leakage from Gradients.\u201d [Online]. Available: arXiv:2001.02610"},{"key":"6533_CR6","unstructured":"Geiping J, Bauermeister H, Dr\u00f6ge H, Moeller M (2020) \u201cInverting Gradients - How easy is it to break privacy in federated learning?\u201d In: Advances in Neural Information Processing Systems, Larochelle H, Ranzato M, Hadsell R, Balcan M\u00a0F, Lin H, (eds), vol\u00a033. Curran Associates, Inc., pp 16937\u201316947"},{"key":"6533_CR7","doi-asserted-by":"crossref","unstructured":"Yin H, Mallya A, Vahdat A, Alvarez J\u00a0M, Kautz J, Molchanov P (2021) \u201cSee through Gradients: Image Batch Recovery via GradInversion,\u201d In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). IEEE, pp 16332\u201316341","DOI":"10.1109\/CVPR46437.2021.01607"},{"key":"6533_CR8","doi-asserted-by":"crossref","unstructured":"Wei W, Liu L, Wut Y, Su G, Iyengar A (2021) \u201cGradient-Leakage Resilient Federated Learning,\u201d In: 2021 IEEE 41st International Conference on Distributed Computing Systems (ICDCS), pp 797\u2013807","DOI":"10.1109\/ICDCS51616.2021.00081"},{"key":"6533_CR9","unstructured":"Dowlin N, Gilad-Bachrach R, Laine K, Lauter K, Naehrig M, Wernsing J (2016) \u201cCryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy,\u201d In: Proceedings of the 33rd International Conference on International Conference on Machine Learning - Volume 48, ser. ICML\u201916. JMLR.org, pp 201\u2013210"},{"key":"6533_CR10","doi-asserted-by":"crossref","unstructured":"Halevi S, Shoup V, \u201cFaster homomorphic linear transformations in helib,\u201d In: Advances in Cryptology-CRYPTO, (2018) 38th Annual International Cryptology Conference, Santa Barbara, CA, USA, 19\u201323 August, 2018, Proceedings, Part I 38. Springer 2018:93\u2013120","DOI":"10.1007\/978-3-319-96884-1_4"},{"key":"6533_CR11","doi-asserted-by":"crossref","unstructured":"Bian S, Wang T, Hiromoto M, Shi Y, Sato T (2020) \u201cENSEI: Efficient Secure Inference via Frequency-Domain Homomorphic Convolution for Privacy-Preserving Visual Recognition,\u201d In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 9403\u20139412","DOI":"10.1109\/CVPR42600.2020.00942"},{"issue":"5","key":"6533_CR12","doi-asserted-by":"publisher","first-page":"1145","DOI":"10.1109\/TC.2021.3076123","volume":"71","author":"G Lloret-Talavera","year":"2022","unstructured":"Lloret-Talavera G, Jorda M, Servat H, Boemer F, Chauhan C, Tomishima S, Shah NN, Pe\u00f1a AJ (2022) Enabling Homomorphically Encrypted Inference for Large DNN Models. IEEE Trans Comput 71(5):1145\u20131155","journal-title":"IEEE Trans Comput"},{"key":"6533_CR13","doi-asserted-by":"crossref","unstructured":"Kanagavelu R, Li Z, Samsudin J, Yang Y, Yang F, Mong Goh RS, Cheah M, Wiwatphonthana P, Akkarajitsakul K, Wang S, \u201cTwo-Phase Multi-Party Computation Enabled Privacy-Preserving Federated Learning,\u201d In, (2020) 20th IEEE\/ACM International Symposium on Cluster. Cloud and Internet Comput (CCGRID) 2020:410\u2013419","DOI":"10.1109\/CCGrid49817.2020.00-52"},{"key":"6533_CR14","doi-asserted-by":"crossref","unstructured":"Zhang C, Ekanut S, Zhen L, Li Z (2022) \u201cAugmented Multi-Party Computation Against Gradient Leakage in Federated Learning,\u201d IEEE Trans Big Data, pp 1\u201310","DOI":"10.1109\/TBDATA.2022.3208736"},{"key":"6533_CR15","unstructured":"Yuhang T, Rui W, Yanqi Q, Emmanouil P, Kaitai L (2023) \u201cFLVoogd: Robust And Privacy Preserving Federated Learning,\u201d In: Proceedings of The 14th Asian Conference on Machine Learning. PMLR, pp 1022\u20131037"},{"key":"6533_CR16","doi-asserted-by":"crossref","unstructured":"Wei K, Li J, Ding M, Ma C, Yang H\u00a0H, Farokhi F, Jin S, Quek T\u00a0Q\u00a0S, Vincent\u00a0Poor H (2020) \u201cFederated Learning With Differential Privacy: Algorithms and Performance Analysis,\u201d IEEE Trans Inf Foren Secur, vol\u00a015, pp 3454\u20133469","DOI":"10.1109\/TIFS.2020.2988575"},{"key":"6533_CR17","doi-asserted-by":"crossref","unstructured":"Naseri M, Hayes J, De\u00a0Cristofaro E (2022) Local and Central Differential Privacy for Robustness and Privacy in Federated Learning. [Online]. Available: arXiv:2009.03561","DOI":"10.14722\/ndss.2022.23054"},{"key":"6533_CR18","unstructured":"Huang Y, Song Z, Li K, Arora S (2020) \u201cInstaHide: Instance-hiding Schemes for Private Distributed Learning,\u201d In: Proceedings of the 37th International Conference on Machine Learning. PMLR, pp 4507\u20134518"},{"key":"6533_CR19","doi-asserted-by":"crossref","unstructured":"Yun S, Han D, Chun S, Oh S\u00a0J, Yoo Y, Choe J (2019) \u201cCutMix: Regularization Strategy to Train Strong Classifiers With Localizable Features,\u201d In: 2019 IEEE\/CVF International Conference on Computer Vision (ICCV). Seoul, Korea (South): IEEE, pp 6022\u20136031","DOI":"10.1109\/ICCV.2019.00612"},{"key":"6533_CR20","unstructured":"Zhang Q, Xin C, Wu H. GALA: Greedy ComputAtion for Linear Algebra in Privacy-Preserved Neural Networks. [Online]. Available: arXiv:2105.01827"},{"key":"6533_CR21","unstructured":"Zhang H, Cisse M, Dauphin Y\u00a0N, Lopez-Paz D (2018) \u201cmixup: Beyond empirical risk minimization,\u201d In: International Conference on Learning Representations, [Online]. Available: https:\/\/openreview.net\/forum?id=r1Ddp1-Rb"},{"key":"6533_CR22","unstructured":"Uddin A\u00a0F M\u00a0S, Monira M\u00a0S, Shin W, Chung T, Bae S-H (2021) \u201cSaliencymix: A saliency guided data augmentation strategy for better regularization,\u201d In: International Conference on Learning Representations, [Online]. Available: https:\/\/openreview.net\/forum?id=-M0QkvBGTTq"},{"key":"6533_CR23","unstructured":"Jeon J, Kim j, Lee K, Oh S, Ok J (2021) \u201cGradient Inversion with Generative Image Prior,\u201d In: Advances in Neural Information Processing Systems, vol\u00a034. Curran Associates, Inc., pp 29898\u201329908"},{"key":"6533_CR24","doi-asserted-by":"crossref","unstructured":"Hitaj B, Ateniese G, Perez-Cruz F (2017) \u201cDeep Models Under the GAN: Information Leakage from Collaborative Deep Learning,\u201d In: Proceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security, ser. CCS \u201917. Ass Comput Mach, pp 603\u2013618","DOI":"10.1145\/3133956.3134012"},{"key":"6533_CR25","unstructured":"Zhang H, Cisse M, Dauphin Y\u00a0N, Lopez-Paz D (2018) \u201cMixup: Beyond Empirical Risk Minimization,\u201d arXiv:1710.09412 [cs, stat],"},{"key":"6533_CR26","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L (2009) \u201cImagenet: A large-scale hierarchical image database,\u201d In: IEEE Conference on Computer Vision and Pattern Recognition 2009:248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6533_CR27","unstructured":"Krizhevsky A, Hinton G, et\u00a0al. (2009) \u201cLearning multiple layers of features from tiny images,\u201d"},{"key":"6533_CR28","doi-asserted-by":"crossref","unstructured":"Deng J, Dong W, Socher R, Li L-J, Li K, Fei-Fei L, \u201cImagenet: A large-scale hierarchical image database,\u201d In: (2009) IEEE conference on computer vision and pattern recognition. Ieee 2009:248\u2013255","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"6533_CR29","doi-asserted-by":"crossref","unstructured":"He K, Zhang X, Ren S, Sun J (2016) \u201cDeep residual learning for image recognition,\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 770\u2013778","DOI":"10.1109\/CVPR.2016.90"},{"key":"6533_CR30","unstructured":"Simonyan K (2014) \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv:1409.1556"},{"key":"6533_CR31","doi-asserted-by":"crossref","unstructured":"Carlini N, Deng S, Garg S, Jha S, Mahloujifar S, Mahmoody M, Thakurta A, Tram\u00e8r F, \u201cIs private learning possible with instance encoding?\u201d In: (2021) IEEE Symposium on Security and Privacy (SP). IEEE 2021:410\u2013427","DOI":"10.1109\/SP40001.2021.00099"},{"key":"6533_CR32","unstructured":"Huang Y, Gupta S, Song Z, Li K, Arora S (2021) \u201cEvaluating Gradient Inversion Attacks and Defenses in Federated Learning,\u201d In: Advances in Neural Information Processing Systems, vol\u00a034. Curran Associates, Inc., pp 7232\u20137241"},{"key":"6533_CR33","unstructured":"Kingma D\u00a0P, Ba J (2014) \u201cAdam: A method for stochastic optimization,\u201d arXiv:1412.6980"},{"key":"6533_CR34","doi-asserted-by":"crossref","unstructured":"Zhang R, Isola P, Efros A\u00a0A, Shechtman E, Wang O (2018) \u201cThe unreasonable effectiveness of deep features as a perceptual metric,\u201d In: Proceedings of the IEEE conference on computer vision and pattern recognition, pp 586\u2013595","DOI":"10.1109\/CVPR.2018.00068"}],"container-title":["Applied Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06533-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10489-025-06533-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10489-025-06533-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,27]],"date-time":"2025-09-27T13:06:21Z","timestamp":1758978381000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10489-025-06533-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":34,"journal-issue":{"issue":"14","published-print":{"date-parts":[[2025,9]]}},"alternative-id":["6533"],"URL":"https:\/\/doi.org\/10.1007\/s10489-025-06533-y","relation":{},"ISSN":["0924-669X","1573-7497"],"issn-type":[{"type":"print","value":"0924-669X"},{"type":"electronic","value":"1573-7497"}],"subject":[],"published":{"date-parts":[[2025,9]]},"assertion":[{"value":"1 April 2025","order":1,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"9 September 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 conflicts of interest to declare that are relevant to the content of this article.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interests"}},{"value":"This article does not contain any studies with human participants or animals performed by any of the authors.","order":3,"name":"Ethics","group":{"name":"EthicsHeading","label":"Ethical and Informed Consent for Data Used"}}],"article-number":"965"}}