{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T23:56:20Z","timestamp":1772927780401,"version":"3.50.1"},"reference-count":28,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"3","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2026,3,1]]},"DOI":"10.1587\/transfun.2025cip0011","type":"journal-article","created":{"date-parts":[[2025,9,7]],"date-time":"2025-09-07T22:07:19Z","timestamp":1757282839000},"page":"327-338","source":"Crossref","is-referenced-by-count":0,"title":["Privacy-Preserving Inference of Machine Learning Models without Retraining"],"prefix":"10.1587","volume":"E109.A","author":[{"given":"Guilherme T S","family":"SATO","sequence":"first","affiliation":[{"name":"Institute of Science Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Wakaha","family":"OGATA","sequence":"additional","affiliation":[{"name":"Institute of Science Tokyo"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","unstructured":"[1] N. Maslej, L. Fattorini, R. Perrault, V. Parli, A. Reuel, E. Brynjolfsson, J. Etchemendy, K. Ligett, T. Lyons, J. Manyika, J.C. Niebles, Y. Shoham, R. Wald, and J. Clark, \u201cThe AI Index 2024 Annual Report,\u201d Stanford University, 2024."},{"key":"2","unstructured":"[2] J. Coronado, M. Stoler, <i>et al.<\/i>, \u201cDeloitte Global Outsourcing Survey 2022,\u201d Deloitte Consulting, LLP, 2022."},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] D. Bartelme and Y. Gorodnichenko, \u201cLinkages and economic development,\u201d National Bureau of Economic Research, 2015. 10.3386\/w21251","DOI":"10.3386\/w21251"},{"key":"4","doi-asserted-by":"crossref","unstructured":"[4] B. Brumen, M. Heri\u010dko, A. Sev\u010dnikar, J. Zavr\u0161nik, and M. H\u00f6lbl, \u201cOutsourcing medical data analyses: Can technology overcome legal, privacy, and confidentiality issues?,\u201d J. Med. Internet Res., vol.15, no.12, p.e283, 2013. 10.2196\/jmir.2471","DOI":"10.2196\/jmir.2471"},{"key":"5","unstructured":"[5] R. Gilad-Bachrach, N. Dowlin, K. Laine, K. Lauter, M. Naehrig, and J. Wernsing, \u201cCryptoNets: Applying neural networks to encrypted data with high throughput and accuracy,\u201d International Conference on Machine Learning, pp.201-210, 2016."},{"key":"6","unstructured":"[6] E. Hesamifard, H. Takabi, and M. Ghasemi, \u201cCryptoDL: Deep Neural Networks over Encrypted Data,\u201d arXiv:1711.05189, 2017. 10.48550\/arXiv.1711.05189"},{"key":"7","unstructured":"[7] C. Juvekar, V. Vaikuntanathan, and A. Chandrakasan, \u201cGAZELLE: A low latency framework for secure neural network inference,\u201d USENIX Security Symposium, pp.1651-1669, 2018."},{"key":"8","doi-asserted-by":"publisher","unstructured":"[8] A. Al Badawi, C. Jin, J. Lin, C.F. Mun, S.J. Jie, B.H.M. Tan, X. Nan, K.M.M. Aung, and V.R. Chandrasekhar, \u201cTowards the AlexNet moment for homomorphic encryption: HCNN, the first homomorphic CNN on encrypted data with GPUs,\u201d IEEE Trans. Emerg. Topics Comput., vol.9, no.3, pp.1330-1343, 2021. 10.1109\/tetc.2020.3014636","DOI":"10.1109\/TETC.2020.3014636"},{"key":"9","doi-asserted-by":"publisher","unstructured":"[9] J.W. Lee, H. Kang, Y. Lee, W. Choi, J. Eom, M. Deryabin, E. Lee, J. Lee, D. Yoo, Y.S. Kim, and J.S. No, \u201cPrivacy-preserving machine learning with fully homomorphic encryption for deep neural network,\u201d IEEE Access, vol.10, pp.30039-30054, 2022. 10.1109\/access.2022.3159694","DOI":"10.1109\/ACCESS.2022.3159694"},{"key":"10","doi-asserted-by":"crossref","unstructured":"[10] G. Huang, Z. Liu, L. Van Der Maaten, and K.Q. Weinberger, \u201cDensely connected convolutional networks,\u201d IEEE Conference on Computer Vision and Pattern Recognition, pp.2261-2269, 2017. 10.1109\/cvpr.2017.243","DOI":"10.1109\/CVPR.2017.243"},{"key":"11","doi-asserted-by":"crossref","unstructured":"[11] J. Liu, M. Juuti, Y. Lu, and N. Asokan, \u201cOblivious neural network predictions via MiniONN transformations,\u201d ACM SIGSAC Conference on Computer and Communications Security, pp.619-631, 2017. 10.1145\/3133956.3134056","DOI":"10.1145\/3133956.3134056"},{"key":"12","doi-asserted-by":"crossref","unstructured":"[12] A.C.C. Yao, \u201cHow to generate and exchange secrets,\u201d Annual Symposium on Foundations of Computer Science, pp.162-167, 1986. 10.1109\/sfcs.1986.25","DOI":"10.1109\/SFCS.1986.25"},{"key":"13","unstructured":"[13] S. Ioffe and C. Szegedy, \u201cBatch normalization: Accelerating deep network training by reducing internal covariate shift,\u201d International Conference on Machine Learning, pp.448-456, 2015."},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] K. Fukushima, \u201cVisual feature extraction by a multilayered network of analog threshold elements,\u201d IEEE Trans. Syst. Sci. Cybern., vol.5, no.4, pp.322-333, 1969. 10.1109\/tssc.1969.300225","DOI":"10.1109\/TSSC.1969.300225"},{"key":"15","unstructured":"[15] A. Krizhevsky, \u201cLearning multiple layers of features from tiny images,\u201d Technical Report, 2009."},{"key":"16","doi-asserted-by":"crossref","unstructured":"[16] O. Russakovsky, J. Deng, H. Su, J. Krause, S. Satheesh, S. Ma, Z. Huang, A. Karpathy, A. Khosla, M. Bernstein, A.C. Berg, and L. Fei-Fei, \u201cImageNet large scale visual recognition challenge,\u201d Int. J. Comput. Vis. (IJCV), vol.115, no.3, pp.211-252, 2015. 10.1007\/s11263-015-0816-y","DOI":"10.1007\/s11263-015-0816-y"},{"key":"17","doi-asserted-by":"crossref","unstructured":"[17] J.H. Cheon, A. Kim, M. Kim, and Y. Song, \u201cHomomorphic encryption for arithmetic of approximate numbers,\u201d Advances in Cryptology - ASIACRYPT, pp.409-437, 2017. 10.1007\/978-3-319-70694-8_15","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] A. Al Badawi, J. Bates, F. Bergamaschi, D.B. Cousins, S. Erabelli, N. Genise, S. Halevi, H. Hunt, A. Kim, Y. Lee, Z. Liu, D. Micciancio, I. Quah, Y. Polyakov, Saraswathy R.v, K. Rohloff, J. Saylor, D. Suponitsky, M. Triplett, V. Vaikuntanathan, and V. Zucca, \u201cOpenFHE: Open-source fully homomorphic encryption library,\u201d Workshop on Encrypted Computing &amp; Applied Homomorphic Cryptography, p.53-63, 2022. 10.1145\/3560827.3563379","DOI":"10.1145\/3560827.3563379"},{"key":"19","doi-asserted-by":"crossref","unstructured":"[19] J.H. Cheon, K. Han, A. Kim, M. Kim, and Y. Song, \u201cA full RNS variant of approximate homomorphic encryption,\u201d Selected Areas in Cryptography - SAC, pp.347-368, 2019. 10.1007\/978-3-030-10970-7_16","DOI":"10.1007\/978-3-030-10970-7_16"},{"key":"20","doi-asserted-by":"crossref","unstructured":"[20] K. He, X. Zhang, S. Ren, and J. Sun, \u201cDeep residual learning for image recognition,\u201d IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp.770-778, June 2016. 10.1109\/CVPR.2016.90","DOI":"10.1109\/CVPR.2016.90"},{"key":"21","unstructured":"[21] K. Simonyan and A. Zisserman, \u201cVery deep convolutional networks for large-scale image recognition,\u201d arXiv:1409.1556, 2015. 10.48550\/arXiv.1409.1556"},{"key":"22","unstructured":"[22] A. Krizhevsky, I. Sutskever, and G.E. Hinton, \u201cImageNet classification with deep convolutional neural networks,\u201d Advances in Neural Information Processing Systems, 2012."},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] C. Szegedy, W. Liu, Y. Jia, P. Sermanet, S. Reed, D. Anguelov, D. Erhan, V. Vanhoucke, and A. Rabinovich, \u201cGoing deeper with convolutions,\u201d arXiv:1409.4842, 2014. 10.48550\/arXiv.1409.4842","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] C. Gentry, \u201cA fully homomorphic encryption scheme,\u201d Ph.D. thesis, Stanford University, 2009.","DOI":"10.1145\/1536414.1536440"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] Y. Bae, J.H. Cheon, W. Cho, J. Kim, and T. Kim, \u201cMETA-BTS: Bootstrapping precision beyond the limit,\u201d ACM SIGSAC Conference on Computer and Communications Security, p.223-234, 2022. 10.1145\/3548606.3560696","DOI":"10.1145\/3548606.3560696"},{"key":"26","doi-asserted-by":"publisher","unstructured":"[26] M.R. Albrecht, R. Player, and S. Scott, \u201cOn the concrete hardness of learning with errors,\u201d Journal of Mathematical Cryptology, vol.9, no.3, pp.169-203, 2015. 10.1515\/jmc-2015-0016","DOI":"10.1515\/jmc-2015-0016"},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] F. Boemer, S. Kim, G. Seifu, F.D. de Souza, V. Gopal, <i>et al.<\/i>, \u201cIntel HEXL (release 1.2),\u201d https:\/\/github.com\/intel\/hexl, 2021.","DOI":"10.1145\/3474366.3486926"},{"key":"28","unstructured":"[28] OpenMP Architecture Review Board, \u201cOpenMP,\u201d https:\/\/www.openmp.org\/, 2021."}],"container-title":["IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E109.A\/3\/E109.A_2025CIP0011\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T04:11:03Z","timestamp":1772856663000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E109.A\/3\/E109.A_2025CIP0011\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,1]]},"references-count":28,"journal-issue":{"issue":"3","published-print":{"date-parts":[[2026]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2025cip0011","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,1]]},"article-number":"2025CIP0011"}}