{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,21]],"date-time":"2026-02-21T04:53:02Z","timestamp":1771649582922,"version":"3.50.1"},"reference-count":51,"publisher":"Association for Computing Machinery (ACM)","issue":"4","license":[{"start":{"date-parts":[[2022,5,3]],"date-time":"2022-05-03T00:00:00Z","timestamp":1651536000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"DOI":"10.13039\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"crossref","award":["2018YFB1403001"],"award-info":[{"award-number":["2018YFB1403001"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":["ACM Trans. Intell. Syst. Technol."],"published-print":{"date-parts":[[2022,8,31]]},"abstract":"<jats:p>\n            Deep Neural Networks (DNNs) have achieved remarkable progress in various real-world applications, especially when abundant training data are provided. However, data isolation has become a serious problem currently. Existing works build privacy-preserving DNN models from either\n            <jats:italic>algorithmic<\/jats:italic>\n            perspective or\n            <jats:italic>cryptographic<\/jats:italic>\n            perspective. The former mainly splits the DNN computation graph between data holders or between data holders and server, which demonstrates good scalability but suffers from accuracy loss and potential privacy risks. In contrast, the latter leverages time-consuming cryptographic techniques, which has strong privacy guarantee but poor scalability. In this article, we propose SPNN\u2014a Scalable and Privacy-preserving deep Neural Network learning framework, from an algorithmic-cryptographic co-perspective. From algorithmic perspective, we split the computation graph of DNN models into two parts, i.e., the private-data-related computations that are performed by data holders and the rest heavy computations that are delegated to a semi-honest server with high computation ability. From cryptographic perspective, we propose using two types of cryptographic techniques, i.e., secret sharing and homomorphic encryption, for the isolated data holders to conduct private-data-related computations privately and cooperatively. Furthermore, we implement SPNN\u00a0in a decentralized setting and introduce user-friendly APIs. Experimental results conducted on real-world datasets demonstrate the superiority of our proposed SPNN.\n          <\/jats:p>","DOI":"10.1145\/3501809","type":"journal-article","created":{"date-parts":[[2022,2,4]],"date-time":"2022-02-04T22:33:18Z","timestamp":1644013998000},"page":"1-21","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":5,"title":["Toward Scalable and Privacy-preserving Deep Neural Network via Algorithmic-Cryptographic Co-design"],"prefix":"10.1145","volume":"13","author":[{"given":"Jun","family":"Zhou","sequence":"first","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China and Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Longfei","family":"Zheng","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1419-964X","authenticated-orcid":false,"given":"Chaochao","family":"Chen","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yan","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Computing, Macquarie University, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaolin","family":"Zheng","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China and JZTData Technology, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Bingzhe","family":"Wu","sequence":"additional","affiliation":[{"name":"Peking University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Cen","family":"Chen","sequence":"additional","affiliation":[{"name":"East China Normal University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"Ant Group, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianwei","family":"Yin","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2022,5,3]]},"reference":[{"key":"e_1_3_2_2_2","unstructured":"Kaggle. [n.d.]. Financial Distress Prediction. Retrieved from https:\/\/www.kaggle.com\/shebrahimi\/financial-distress."},{"key":"e_1_3_2_3_2","doi-asserted-by":"publisher","DOI":"10.1145\/2976749.2978318"},{"issue":"4","key":"e_1_3_2_4_2","first-page":"79","article-title":"A survey on homomorphic encryption schemes: Theory and implementation","volume":"51","author":"Acar Abbas","year":"2018","unstructured":"Abbas Acar, Hidayet Aksu, A. Selcuk Uluagac, and Mauro Conti. 2018. A survey on homomorphic encryption schemes: Theory and implementation. ACM Comput. Surveys 51, 4 (2018), 79.","journal-title":"ACM Comput. Surveys"},{"key":"e_1_3_2_5_2","doi-asserted-by":"publisher","DOI":"10.1145\/3319535.3339819"},{"key":"e_1_3_2_6_2","first-page":"420","volume-title":"Proceedings of the Annual International Cryptology Conference","author":"Beaver Donald","year":"1991","unstructured":"Donald Beaver. 1991. Efficient multiparty protocols using circuit randomization. In Proceedings of the Annual International Cryptology Conference. Springer, 420\u2013432."},{"key":"e_1_3_2_7_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-16145-3_16"},{"key":"e_1_3_2_8_2","doi-asserted-by":"publisher","DOI":"10.1145\/3394138"},{"key":"e_1_3_2_9_2","doi-asserted-by":"publisher","DOI":"10.1186\/s12920-018-0397-z"},{"key":"e_1_3_2_10_2","unstructured":"Valerie Chen Valerio Pastro and Mariana Raykova. 2019. Secure computation for machine learning with SPDZ. Retrieved from https:\/\/arXiv:1901.00329."},{"key":"e_1_3_2_11_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2014.02.026"},{"key":"e_1_3_2_12_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-32009-5_38"},{"key":"e_1_3_2_13_2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-14577-3_13"},{"key":"e_1_3_2_14_2","doi-asserted-by":"publisher","DOI":"10.14722\/ndss.2015.23113"},{"key":"e_1_3_2_15_2","doi-asserted-by":"publisher","DOI":"10.1145\/3340531.3411903"},{"key":"e_1_3_2_16_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2005.10.010"},{"key":"e_1_3_2_17_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243834"},{"key":"e_1_3_2_18_2","first-page":"201","volume-title":"Proceedings of the International Conference on machine Learning (ICML\u201916)","author":"Gilad-Bachrach Ran","year":"2016","unstructured":"Ran Gilad-Bachrach, Nathan Dowlin, Kim Laine, Kristin Lauter, Michael Naehrig, and John Wernsing. 2016. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In Proceedings of the International Conference on machine Learning (ICML\u201916). 201\u2013210."},{"key":"e_1_3_2_19_2","first-page":"315","volume-title":"Proceedings of the 14th International Conference on Artificial Intelligence and Statistics","author":"Glorot Xavier","year":"2011","unstructured":"Xavier Glorot, Antoine Bordes, and Yoshua Bengio. 2011. Deep sparse rectifier neural networks. In Proceedings of the 14th International Conference on Artificial Intelligence and Statistics. 315\u2013323."},{"key":"e_1_3_2_20_2","volume-title":"Foundations of Cryptography: Volume 2, Basic Applications","author":"Goldreich Oded","year":"2009","unstructured":"Oded Goldreich. 2009. Foundations of Cryptography: Volume 2, Basic Applications. Cambridge University Press."},{"key":"e_1_3_2_21_2","doi-asserted-by":"publisher","DOI":"10.5555\/3086952"},{"key":"e_1_3_2_22_2","unstructured":"Zhongshu Gu Heqing Huang Jialong Zhang Dong Su Ankita Lamba Dimitrios Pendarakis and Ian Molloy. 2019. Securing input data of deep learning inference systems via partitioned enclave execution. Retrieved from https:\/\/abs\/1807.00969."},{"key":"e_1_3_2_23_2","doi-asserted-by":"publisher","DOI":"10.1016\/j.jnca.2018.05.003"},{"issue":"4","key":"e_1_3_2_24_2","first-page":"669","article-title":"Secure multiple linear regression based on homomorphic encryption","volume":"27","author":"Hall Rob","year":"2011","unstructured":"Rob Hall, Stephen E. Fienberg, and Yuval Nardi. 2011. Secure multiple linear regression based on homomorphic encryption. J. Offic. Stat. 27, 4 (2011), 669.","journal-title":"J. Offic. Stat."},{"key":"e_1_3_2_25_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-59497-3_175"},{"key":"e_1_3_2_26_2","unstructured":"Ehsan Hesamifard Hassan Takabi and Mehdi Ghasemi. 2017. Cryptodl: Deep neural networks over encrypted data. Retrieved from https:\/\/arXiv:1711.05189."},{"key":"e_1_3_2_27_2","unstructured":"Andrew G. Howard Menglong Zhu Bo Chen Dmitry Kalenichenko Weijun Wang Tobias Weyand Marco Andreetto and Hartwig Adam. 2017. Mobilenets: Efficient convolutional neural networks for mobile vision applications. Retrieved from https:\/\/arXiv:1704.04861."},{"key":"e_1_3_2_28_2","doi-asserted-by":"publisher","DOI":"10.1038\/35016072"},{"key":"e_1_3_2_29_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330765"},{"key":"e_1_3_2_30_2","first-page":"1651","volume-title":"Proceedings of the 27th USENIX Security Symposium (USENIX Security\u201918)","author":"Juvekar Chiraag","year":"2018","unstructured":"Chiraag Juvekar, Vinod Vaikuntanathan, and Anantha Chandrakasan. 2018. \\( \\lbrace \\) GAZELLE \\( \\rbrace \\) : A low latency framework for secure neural network inference. In Proceedings of the 27th USENIX Security Symposium (USENIX Security\u201918). 1651\u20131669."},{"key":"e_1_3_2_31_2","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"e_1_3_2_32_2","doi-asserted-by":"publisher","DOI":"10.1145\/3292500.3330920"},{"key":"e_1_3_2_33_2","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401253"},{"issue":"1","key":"e_1_3_2_34_2","article-title":"Innovative instructions and software model for isolated execution.","volume":"10","author":"McKeen Frank","year":"2013","unstructured":"Frank McKeen, Ilya Alexandrovich, Alex Berenzon, Carlos V Rozas, Hisham Shafi, Vedvyas Shanbhogue, and Uday R Savagaonkar. 2013. Innovative instructions and software model for isolated execution.Hasp@ isca 10, 1 (2013).","journal-title":"Hasp@ isca"},{"key":"e_1_3_2_35_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2019.00029"},{"key":"e_1_3_2_36_2","doi-asserted-by":"publisher","DOI":"10.1145\/3243734.3243760"},{"key":"e_1_3_2_37_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.12"},{"key":"e_1_3_2_38_2","unstructured":"Seyed Ali Osia Ali Shahin Shamsabadi Ali Taheri Kleomenis Katevas Sina Sajadmanesh Hamid R Rabiee Nicholas D Lane and Hamed Haddadi. 2019. A hybrid deep learning architecture for privacy-preserving mobile analytics. Retrieved from https:\/\/arXiv:1703.02952."},{"key":"e_1_3_2_39_2","doi-asserted-by":"publisher","DOI":"10.1007\/3-540-48910-X_16"},{"key":"e_1_3_2_40_2","first-page":"8024","volume-title":"Advances in Neural Information Processing Systems","author":"Paszke Adam","year":"2019","unstructured":"Adam Paszke, Sam Gross, Francisco Massa, Adam Lerer, James Bradbury, Gregory Chanan, Trevor Killeen, Zeming Lin, Natalia Gimelshein, Luca Antiga et\u00a0al. 2019. PyTorch: An imperative style, high-performance deep learning library. In Advances in Neural Information Processing Systems. MIT Press, 8024\u20138035."},{"key":"e_1_3_2_41_2","doi-asserted-by":"publisher","DOI":"10.1145\/3459637.3482252"},{"key":"e_1_3_2_42_2","first-page":"797","volume-title":"Proceedings of the USENIX Security Conference","author":"Pinkas Benny","year":"2014","unstructured":"Benny Pinkas, Thomas Schneider, and Michael Zohner. 2014. Faster private set intersection based on \\( \\lbrace \\) OT \\( \\rbrace \\) extension. In Proceedings of the USENIX Security Conference. 797\u2013812."},{"key":"e_1_3_2_43_2","doi-asserted-by":"publisher","DOI":"10.1145\/3195970.3196023"},{"key":"e_1_3_2_44_2","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2017.41"},{"key":"e_1_3_2_45_2","unstructured":"Praneeth Vepakomma Otkrist Gupta Tristan Swedish and Ramesh Raskar. 2018. Split learning for health: Distributed deep learning without sharing raw patient data. Retrieved from https:\/\/arXiv:1812.00564."},{"key":"e_1_3_2_46_2","first-page":"24","article-title":"SecureNN: 3-Party secure computation for neural network training","volume":"1","author":"Wagh Sameer","year":"2019","unstructured":"Sameer Wagh, Divya Gupta, and Nishanth Chandran. 2019. SecureNN: 3-Party secure computation for neural network training. Proc. Privacy Enhanc. Technol. 1 (2019), 24.","journal-title":"Proc. Privacy Enhanc. Technol."},{"key":"e_1_3_2_47_2","first-page":"681","volume-title":"Proceedings of the 28th International Conference on Machine Learning (ICML\u201911)","author":"Welling Max","year":"2011","unstructured":"Max Welling and Yee Whye Teh. 2011. Bayesian learning via stochastic gradient langevin dynamics. In Proceedings of the 28th International Conference on Machine Learning (ICML\u201911). 681\u2013688. Retrieved from https:\/\/icml.cc\/2011\/papers\/398_icmlpaper.pdf."},{"key":"e_1_3_2_48_2","article-title":"Characterizing membership privacy in stochastic gradient langevin dynamics","author":"Wu Bingzhe","year":"2019","unstructured":"Bingzhe Wu, Chaochao Chen, Shiwan Zhao, Cen Chen, Yuan Yao, Guangyu Sun, Li Wang, Xiaolu Zhang, and Jun Zhou. 2019. Characterizing membership privacy in stochastic gradient langevin dynamics. In Proceedings of the AAAI.","journal-title":"Proceedings of the AAAI"},{"key":"e_1_3_2_49_2","unstructured":"Runhua Xu James B. D. Joshi and Chao Li. 2019. CryptoNN: Training neural networks over encrypted data. Retrieved from https:\/\/arXiv:1904.07303."},{"key":"e_1_3_2_50_2","doi-asserted-by":"publisher","DOI":"10.1145\/3298981"},{"key":"e_1_3_2_51_2","doi-asserted-by":"publisher","DOI":"10.1109\/TPDS.2013.18"},{"key":"e_1_3_2_52_2","doi-asserted-by":"publisher","DOI":"10.1145\/3357384.3357992"}],"container-title":["ACM Transactions on Intelligent Systems and Technology"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501809","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3501809","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T18:09:48Z","timestamp":1750183788000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3501809"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022,5,3]]},"references-count":51,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2022,8,31]]}},"alternative-id":["10.1145\/3501809"],"URL":"https:\/\/doi.org\/10.1145\/3501809","relation":{},"ISSN":["2157-6904","2157-6912"],"issn-type":[{"value":"2157-6904","type":"print"},{"value":"2157-6912","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022,5,3]]},"assertion":[{"value":"2021-01-01","order":0,"name":"received","label":"Received","group":{"name":"publication_history","label":"Publication History"}},{"value":"2021-11-01","order":1,"name":"accepted","label":"Accepted","group":{"name":"publication_history","label":"Publication History"}},{"value":"2022-05-03","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}