{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,2]],"date-time":"2026-09-02T05:27:04Z","timestamp":1788326824600,"version":"build-2803163510"},"reference-count":34,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"},{"start":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T00:00:00Z","timestamp":1708905600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Intell Syst"],"abstract":"<jats:title>Abstract<\/jats:title><jats:p>How to protect the privacy of training data in deep learning has been the subject of increasing amounts of related research in recent years. Private Aggregation of Teacher Ensembles (PATE) uses transfer learning and differential privacy methods to provide a broadly applicable data privacy framework in deep learning. PATE combines the Laplacian mechanism and the voting method to achieve deep learning privacy classification. However, the Laplacian mechanism may greatly distort the histogram vote counts of each class. This paper proposes a novel exponential mechanism with PATE to ensure the privacy protection. This proposed method improves the protection effect and accuracy through the screening algorithm and uses the differential privacy combination theorems to reduce the total privacy budget. The data-dependent analysis demonstrates that the exponential mechanism outperforms the original Laplace mechanism. Experimental results show that the proposed method can train models with improved accuracy while requiring a smaller privacy budget when compared to the original Pate framework.<\/jats:p>","DOI":"10.1007\/s44196-024-00422-x","type":"journal-article","created":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T13:02:40Z","timestamp":1708952560000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":7,"title":["Privacy-Preserving Classification on Deep Learning with Exponential Mechanism"],"prefix":"10.1007","volume":"17","author":[{"given":"Quan","family":"Ju","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rongqing","family":"Xia","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8625-0778","authenticated-orcid":false,"given":"Shuhong","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiaojian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,2,26]]},"reference":[{"issue":"6","key":"422_CR1","volume":"8","author":"Y Li","year":"2018","unstructured":"Li, Y., Zhang, H., Xue, X., Jiang, Y., Shen, Q.: Deep learning for remote sensing image classification: a survey. Wiley Interdisciplinary Rev. 8(6), e1264 (2018)","journal-title":"Wiley Interdisciplinary Rev."},{"issue":"4","key":"422_CR2","doi-asserted-by":"publisher","DOI":"10.1117\/1.OE.58.4.040901","volume":"58","author":"W Wang","year":"2019","unstructured":"Wang, W., Yang, Y., Wang, X., Wang, W., Li, J.: Development of convolutional neural network and its application in image classification: a survey. Opt. Eng. 58(4), 040901 (2019)","journal-title":"Opt. Eng."},{"key":"422_CR3","unstructured":"Zou, Z., Shi, Z., Guo, Y., Ye, J.: Object detection in 20 years: A survey. arXiv preprint arXiv:1905.05055.019, (2019)"},{"issue":"2","key":"422_CR4","doi-asserted-by":"publisher","first-page":"117","DOI":"10.1007\/s41095-019-0149-9","volume":"5","author":"A Borji","year":"2019","unstructured":"Borji, A., Cheng, M.-M., Hou, Q., Jiang, H., Li, J.: Salient object detection: a survey. Comput. Visual Media 5(2), 117 (2019)","journal-title":"Comput. Visual Media"},{"issue":"1","key":"422_CR5","first-page":"48","volume":"6","author":"C Sukanya","year":"2016","unstructured":"Sukanya, C., Gokul, R., Paul, V.: A survey on object recognition methods. Int. J. Sci. Eng. Comput. Technol. 6(1), 48 (2016)","journal-title":"Int. J. Sci. Eng. Comput. Technol."},{"key":"422_CR6","doi-asserted-by":"crossref","unstructured":"Zhou, T., Fan, D.-P., Cheng, M.-M., Shen, J., Shao, L.: Rgb-d salient object detection: A survey. Computational Visual Media, 1, (2021)","DOI":"10.1007\/s41095-020-0199-z"},{"key":"422_CR7","doi-asserted-by":"crossref","unstructured":"Xie, S., Girshick, R., Dollar, P., Tu, Z., He, K.: Aggregated residual transformations for deep neural networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 1492 (2017)","DOI":"10.1109\/CVPR.2017.634"},{"key":"422_CR8","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE conference on computer vision and pattern recognition, 7132 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"422_CR9","doi-asserted-by":"crossref","unstructured":"Li, X., Wang, W., Hu, X., Yang, J.: Selective kernel networks. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, 510 (2019)","DOI":"10.1109\/CVPR.2019.00060"},{"key":"422_CR10","doi-asserted-by":"publisher","first-page":"125","DOI":"10.1016\/j.ins.2022.11.065","volume":"620","author":"X Shaorong","year":"2023","unstructured":"Shaorong, X., Zhenyu, Z., Hang, Y., Xiangfeng, L.: Recurrent prediction model for partially observable MDPs. Inf. Sci. 620, 125\u2013141 (2023)","journal-title":"Inf. Sci."},{"key":"422_CR11","doi-asserted-by":"crossref","unstructured":"McSherry, F., Talwar, K. Mechanism Design via Differential Privacy. In Proceedings of the 48th Annual IEEE Symposium on Foundations of Computer Science. New York, USA, (2007)","DOI":"10.1109\/FOCS.2007.66"},{"key":"422_CR12","unstructured":"Fay, D., Sj\u00f6lund, J., Oechtering, T.J.: Decentralized differentially private segmentation with pate. arXiv: 2004.06567 (2020)"},{"key":"422_CR13","unstructured":"Papernot, N., Abadi, M., Erlingsson, \u00da., Goodfellow, I., Talwar, K.: Semi-supervised Knowledge Transfer for Deep Learning from Private Training Data. arXiv: 1610.05755 (2016)"},{"key":"422_CR14","unstructured":"Long, Y., Wang, B., Yang, Z.: G-PATE: Scalable Differentially Private Data Generator via Private Aggregation of Teacher Discriminators. arXiv: 1906.09338 (2021)"},{"key":"422_CR15","first-page":"123","volume":"24","author":"C Li","year":"2010","unstructured":"Li, C., Hay, M., Rastogi, V., Miklau, G., McGregor, A.: Optimizing Linear Counting Queries under Differential Privacy. VLDB J. 24, 123\u2013134 (2010)","journal-title":"VLDB J."},{"issue":"1","key":"422_CR16","first-page":"101","volume":"37","author":"P Xiong","year":"2014","unstructured":"Xiong, P., Zhu, T., Wang, X.: A survey on differential privacy proception and application. Chin. J. Comput. 37(1), 101\u2013122 (2014)","journal-title":"Chin. J. Comput."},{"key":"422_CR17","doi-asserted-by":"crossref","unstructured":"Dwork, C., RothblumG, N., Vadhan, S.: Boosting and differential privacy. In Proceedings of of the 51st EEE Annual Symposium on Foun-dations of Computer Science. Piscataway, United States, (2010)","DOI":"10.1109\/FOCS.2010.12"},{"key":"422_CR18","doi-asserted-by":"crossref","unstructured":"Dwork, C. Differential privacy.: In Proceedings of the 33rd International Colloquium on Automata, Languages, and Programming. Berlin, Germany, (2006)","DOI":"10.1007\/11787006_1"},{"issue":"2","key":"422_CR19","first-page":"346","volume":"57","author":"J Liu","year":"2020","unstructured":"Liu, J., Meng, X.: Survey on privacy-presserving machine learning. J. Comput. Res. Dev. (China) 57(2), 346\u2013362 (2020)","journal-title":"J. Comput. Res. Dev. (China)"},{"key":"422_CR20","doi-asserted-by":"crossref","unstructured":"Sweeney, L.: Achieving k-anonymity privacy protection using generalization, and suppression. Int. J. Uncertainty, Fuzziness Knowl.-Based Syst., 571\u2013588 (2002)","DOI":"10.1142\/S021848850200165X"},{"key":"422_CR21","doi-asserted-by":"crossref","unstructured":"Kumar, P., Mayil, V., Karthikeyan. M.: L Diversity on K-Anonymity with External Database for improving Privacy Preserving Data Publishing. Int. J. Comput. Appl., 54(14), 7\u201313 (2012)","DOI":"10.5120\/8632-2341"},{"key":"422_CR22","doi-asserted-by":"crossref","unstructured":"Machanavajjhala, A., Kifer, D., Gehrke, J.: L-diversity: Privacy beyond k-anonymity. Acm Trans. Knowl. Discovery Data, 1.1, 3-es (2007)","DOI":"10.1145\/1217299.1217302"},{"key":"422_CR23","doi-asserted-by":"crossref","unstructured":"Li, N., Li, T., Venkatasubramanian, S.: t-Closeness: Privacy Beyond k-Anonymity and l-Diversity. In Proceedings of the International Conference on Data Engineering IEEE, Istanbul, Turkey, 15\u201317 April 2007 (2007)","DOI":"10.1109\/ICDE.2007.367856"},{"key":"422_CR24","unstructured":"Jordon, J., Yoon, J., Van Der Schaar M.: PATE-GAN: Generating synthetic data with differential privacy guarantees. In Proceedings of the International conference on learning representtations. New Orleans, United States, 6- 9 May 2019 (2019)"},{"key":"422_CR25","doi-asserted-by":"crossref","unstructured":"Dwork, C., Kenthapadi, K., McSherry, F., Mironov, I., Naor, M.: Our data, ourselves: Privacy via distributed noise generation. In Proceedings of the 25th annual international conference on the theory and applications of cryptographic techniques, St. Petersburg, Russia, 28 May-1 June 2006 (2006)","DOI":"10.1007\/11761679_29"},{"issue":"9","key":"422_CR26","doi-asserted-by":"publisher","first-page":"89","DOI":"10.1145\/1810891.1810916","volume":"53","author":"F Mcsherry","year":"2010","unstructured":"Mcsherry, F.: Privacy integrated queries: an extensible platform for privacy-preserving data analysis. Commun. ACM 53(9), 89\u201397 (2010)","journal-title":"Commun. ACM"},{"key":"422_CR27","doi-asserted-by":"crossref","unstructured":"Kifer, D., Lin, B. R.: Towards an axiomatization of statistical privacy and utility. In Proceedings of the Twenty-Ninth ACM Sigmod-Sigact-Sigart Symposium on Principles of Database Systems, Indianapolis, Usa, 6\u201311 June 2010 (2010)","DOI":"10.1145\/1807085.1807106"},{"key":"422_CR28","doi-asserted-by":"crossref","unstructured":"Dwork, C., Mcsherry, F., Nissim, K.: Calibrating Noise to Sensitivity in Private Data Analysis. In Proceedings of the Vldb, Seoul, Korea, from 12\u201315 September 2006 (2006)","DOI":"10.1007\/11681878_14"},{"issue":"3\u20134","key":"422_CR29","first-page":"211","volume":"9","author":"C Dwork","year":"2014","unstructured":"Dwork, C., Roth, A.: The algorithmie foundations of differential privacy. Found. Trends Theoretical Comput. Sci. 9(3\u20134), 211\u2013407 (2014)","journal-title":"Found. Trends Theoretical Comput. Sci."},{"key":"422_CR30","unstructured":"Roughgarden, G.A., Sundararajan, M.: Universally Utility-Maximizing Privacy Mechanism. In Proceedings of the 41st annual acm symposium on theory of computing. bethesda, United States, 31 May-2 June 2009 (2009)"},{"key":"422_CR31","doi-asserted-by":"crossref","unstructured":"Abadi, M., Chu, A., Godfellow, I.: Deep learming with differential privacy. In Proceedings of the ACM SIGSAC Conference on Com-puter and Comm unications Security. Vienna, Austria, 24\u201328 October 2016 (2016)","DOI":"10.1145\/2976749.2978318"},{"key":"422_CR32","unstructured":"LeCun, Y., Cortes, C., Burges, CJ.: MNIST handwritten digit database. ATT Labs [Online], 2, (2010)"},{"key":"422_CR33","unstructured":"Alex K.: Learning multiple layers of features from tiny images. (2009)"},{"issue":"5","key":"422_CR34","first-page":"92","volume":"3","author":"X Li","year":"2018","unstructured":"Li, X., Li, H., Li, F.: A Survey on Differential Privacy. J. Cyber Secur. (China) 3(5), 92\u2013104 (2018)","journal-title":"J. Cyber Secur. (China)"}],"container-title":["International Journal of Computational Intelligence Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-024-00422-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s44196-024-00422-x\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s44196-024-00422-x.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,26]],"date-time":"2024-02-26T13:08:15Z","timestamp":1708952895000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s44196-024-00422-x"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2,26]]},"references-count":34,"journal-issue":{"issue":"1","published-online":{"date-parts":[[2024,12]]}},"alternative-id":["422"],"URL":"https:\/\/doi.org\/10.1007\/s44196-024-00422-x","relation":{},"ISSN":["1875-6883"],"issn-type":[{"value":"1875-6883","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,2,26]]},"assertion":[{"value":"11 August 2023","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"29 January 2024","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 February 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of Interest"}}],"article-number":"39"}}