{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,17]],"date-time":"2026-03-17T00:19:10Z","timestamp":1773706750144,"version":"3.50.1"},"reference-count":40,"publisher":"Institute of Electronics, Information and Communications Engineers (IEICE)","issue":"12","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEICE Trans. Fundamentals"],"published-print":{"date-parts":[[2020,12,1]]},"DOI":"10.1587\/transfun.2020tap0011","type":"journal-article","created":{"date-parts":[[2020,11,30]],"date-time":"2020-11-30T22:15:22Z","timestamp":1606774522000},"page":"1367-1380","source":"Crossref","is-referenced-by-count":5,"title":["Efficient Secure Neural Network Prediction Protocol Reducing Accuracy Degradation"],"prefix":"10.1587","volume":"E103.A","author":[{"given":"Naohisa","family":"NISHIDA","sequence":"first","affiliation":[{"name":"Panasonic Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tatsumi","family":"OBA","sequence":"additional","affiliation":[{"name":"Panasonic Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuji","family":"UNAGAMI","sequence":"additional","affiliation":[{"name":"Panasonic Corporation"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jason","family":"PAUL CRUZ","sequence":"additional","affiliation":[{"name":"Osaka University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Naoto","family":"YANAI","sequence":"additional","affiliation":[{"name":"Osaka University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Tadanori","family":"TERUYA","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nuttapong","family":"ATTRAPADUNG","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Takahiro","family":"MATSUDA","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Goichiro","family":"HANAOKA","sequence":"additional","affiliation":[{"name":"National Institute of Advanced Industrial Science and Technology"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"532","reference":[{"key":"1","doi-asserted-by":"crossref","unstructured":"[1] V. Gulshan, L. Peng, and M. Coram, \u201cDevelopment and validation of a deep learning algorithm for detection of diabetic retinopathy in retinal fundus photographs,\u201d JAMA, vol.316, pp.2402-2410, 2016. 10.1001\/jama.2016.17216","DOI":"10.1001\/jama.2016.17216"},{"key":"2","doi-asserted-by":"crossref","unstructured":"[2] F. Schroff, D. Kalenichenko, and J. Philbin, \u201cFaceNet: A unified embedding for face recognition and clustering,\u201d Proc. CVPR 2015, pp.815-823, IEEE, 2015. 10.1109\/cvpr.2015.7298682","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"3","doi-asserted-by":"crossref","unstructured":"[3] M. Barni, C. Orlandi, and A. Piva, \u201cA privacy-preserving protocol for neural-network-based computation,\u201d Proc. MM&Sec 2006, pp.146-151, ACM, 2006. 10.1145\/1161366.1161393","DOI":"10.1145\/1161366.1161393"},{"key":"4","doi-asserted-by":"publisher","unstructured":"[4] C. Orlandi, A. Piva, and M. Barni, \u201cOblivious neural network computing via homomorphic encryption,\u201d EURASIP J. Inform. Secur., vol.2007, no.1, 2007. 10.1186\/1687-417x-2007-037343","DOI":"10.1186\/1687-417X-2007-037343"},{"key":"5","doi-asserted-by":"crossref","unstructured":"[5] R. Bost, R.A. Popa, S. Tu, and S. Goldwasser, \u201cMachine learning classification over encrypted data,\u201d Proc. NDSS 2015, Internet Society, 2015. 10.14722\/ndss.2015.23241","DOI":"10.14722\/ndss.2015.23241"},{"key":"6","doi-asserted-by":"crossref","unstructured":"[6] J. Liu, M. Juuti, Y. Lu, and N. Asokan, \u201cOblivious neural network predictions via minionn transformations,\u201d Proc. CCS 2017, pp.619-631, ACM, 2017. 10.1145\/3133956.3134056","DOI":"10.1145\/3133956.3134056"},{"key":"7","unstructured":"[7] B.D. Rouhani, M.S. Riazi, and F. Koushanfar, \u201cDeepsecure: Scalable provably-secure deep learning,\u201d arXiv:1705.08963, 2017."},{"key":"8","unstructured":"[8] N. Chandran, D. Gupta, A. Rastogi, R. Sharma, and S. Tripathi, \u201cEzPC: Programmable, efficient, and scalable secure two-party computation for machine learning,\u201d IACR ePrint Archive, https:\/\/eprint.iacr.org\/2017\/1109, 2017."},{"key":"9","doi-asserted-by":"crossref","unstructured":"[9] M.S. Riazi, C. Weinert, O. Tkachenko, E.M. Songhori, T. Schneider, and F. Koushanfar, \u201cChameleon: A hybrid secure computation framework for machine learning applications,\u201d Proc. ASIACCS 2018, pp.707-721, ACM, 2018. 10.1145\/3196494.3196522","DOI":"10.1145\/3196494.3196522"},{"key":"10","unstructured":"[10] C. Juvekar, V. Vaikuntanathan, and A. Chandrakasan, \u201cGazelle: A low latency framework for secure neural network inference,\u201d Proc. of Usenix Security 2018, pp.1651-1669, Usenix Association, 2018."},{"key":"11","unstructured":"[11] Z. Yang, Z. Dai, Y. Yang, J.G. Carbonell, R. Salakhutdinov, and Q.V. Le, \u201cXLNet: Generalized autoregressive pretraining for language understanding,\u201d arXiv preprint arXiv:1906.08237, 2019."},{"key":"12","unstructured":"[12] A. Dalskov, D. Escudero, and M. Keller, \u201cSecure evaluation of quantized neural networks,\u201d arXiv preprint arXiv:1910.12435, 2019."},{"key":"13","doi-asserted-by":"crossref","unstructured":"[13] P. Mohassel and Y. Zhang, \u201cSecureML: A system for scalable privacy-preserving machine learning,\u201d Proc. IEEE S&P, pp.19-38, IEEE, 2017. 10.1109\/sp.2017.12","DOI":"10.1109\/SP.2017.12"},{"key":"14","doi-asserted-by":"publisher","unstructured":"[14] H. Kitai, J.P. Cruz, N. Yanai, N. Nishida, T. Oba, Y. Unagami, T. Teruya, N. Attrapadung, T. Matsuda, and G. Hanaoka, \u201cMOBIUS: model-oblivious binarized neural networks,\u201d IEEE Access, vol.7, pp.139021-139034, 2019. 10.1109\/access.2019.2939410","DOI":"10.1109\/ACCESS.2019.2939410"},{"key":"15","unstructured":"[15] P. Mohassel and P. Rindal, \u201cABY3: A mixed protocol framework for machine learning,\u201d IACR ePrint Archive, https:\/\/eprint.iacr.org\/2018\/403, 2018."},{"key":"16","unstructured":"[16] N. Dowlin, 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 Proc. ICML 2016, pp.201-210, 2016."},{"key":"17","unstructured":"[17] M. Chase, R. Gilad-Bachrach, K. Laine, K. Lauter, and P. Rindal, \u201cPrivate collaborative neural network learning,\u201d IACR ePrint Archive, https:\/\/eprint.iacr.org\/2017\/762, 2017."},{"key":"18","doi-asserted-by":"crossref","unstructured":"[18] F. Bourse, M. Minelli, M. Minihold, and P. Paillier, \u201cFast homomorphic evaluation of deep discretized neural networks,\u201d IACR ePrint Archive, https:\/\/eprint.iacr.org\/2017\/1114, 2017.","DOI":"10.1007\/978-3-319-96878-0_17"},{"key":"19","unstructured":"[19] S. Wagh, D. Gupta, and N. Chandran, \u201cSecureNN: Efficient and private neural network training,\u201d IACR ePrint Archive, https:\/\/eprint.iacr.org\/2018\/442, 2018."},{"key":"20","unstructured":"[20] A. Sanyal, M. Kusner, A. Gascon, and V. Kanade, \u201cTAPAS: Tricks to accelerate (encrypted) prediction as a service,\u201d Proc. ICML 2018, pp.4490-4499, 2018."},{"key":"21","doi-asserted-by":"crossref","unstructured":"[21] S. Halevi and V. Shoup, \u201cBootstrapping for helib,\u201d Proc. EUROCRYPT 2015, LNCS, vol.9056, pp.641-670, Springer, 2015. 10.1007\/978-3-662-46800-5_25","DOI":"10.1007\/978-3-662-46800-5_25"},{"key":"22","doi-asserted-by":"crossref","unstructured":"[22] C. Gentry, \u201cFully homomorphic encryption using ideal lattice,\u201d Proc. STOC 2009, pp.169-178, ACM, 2009. 10.1145\/1536414.1536440","DOI":"10.1145\/1536414.1536440"},{"key":"23","doi-asserted-by":"crossref","unstructured":"[23] E. Makri, D. Rotaru, N.P. Smart, and F. Vercauteren, \u201cEPIC: Efficient private image classification (or: Learning from the masters),\u201d Proc. CT-RSA 2019, LNCS, vol.11405, pp.473-492, Springer, 2019. 10.1007\/978-3-030-12612-4_24","DOI":"10.1007\/978-3-030-12612-4_24"},{"key":"24","doi-asserted-by":"crossref","unstructured":"[24] L. Melis, C. Song, E. De Cristofaro, and V. Shmatikov, \u201cExploiting unintended feature leakage in collaborative learning,\u201d Proc. IEEE S&P 2019, pp.691-706, IEEE, 2019. 10.1109\/sp.2019.00029","DOI":"10.1109\/SP.2019.00029"},{"key":"25","doi-asserted-by":"crossref","unstructured":"[25] Z. He, T. Zhang, and R.B. Lee, \u201cModel inversion attacks against collaborative inference,\u201d Proc. ACSAC 2019, pp.148-162, ACM, 2019. 10.1145\/3359789.3359824","DOI":"10.1145\/3359789.3359824"},{"key":"26","unstructured":"[26] F. Tram\u00e8r, F. Zhang, A. Juels, M.K. Reiter, and T. Ristenpart, \u201cStealing machine learning models via prediction apis,\u201d Proc. Usenix Security 2016, pp.601-618, Usenix Association, 2016."},{"key":"27","doi-asserted-by":"crossref","unstructured":"[27] M. Kesarwani, B. Mukhoty, V. Arya, and S. Mehta, \u201cModel extraction warning in mlaas paradigm,\u201d Proc. ACSAC 2018, pp.371-380, ACM, 2018. 10.1145\/3274694.3274740","DOI":"10.1145\/3274694.3274740"},{"key":"28","unstructured":"[28] S. Szyller, B.G. Atli, S. Marchal, and N. Asokan, \u201cDAWN: Dynamic adversarial watermarking of neural networks,\u201d arXiv preprint, http:\/\/arxiv.org\/abs\/1906.00830, 2019."},{"key":"29","unstructured":"[29] M. Courbariaux, I. Hubara, D. Soudry, R. El-Yaniv, and Y. Bengio, \u201cBinarized neural networks: Training deep neural networks with weights and activations constrained to +1 or -1,\u201d arXiv preprint, https:\/\/arxiv.org\/abs\/1602.02830, 2016."},{"key":"30","doi-asserted-by":"crossref","unstructured":"[30] A. Shamir, \u201cHow to share a secret,\u201d Commun. ACM, vol.22, no.11, pp.612-613, 1979. 10.1145\/359168.359176","DOI":"10.1145\/359168.359176"},{"key":"31","doi-asserted-by":"crossref","unstructured":"[31] G. Blakley, \u201cSafeguarding cryptographic keys,\u201d Proc. National Computer Conference, pp.313-317, 1979. 10.1109\/mark.1979.8817296","DOI":"10.1109\/MARK.1979.8817296"},{"key":"32","doi-asserted-by":"publisher","unstructured":"[34] R. Canetti, \u201cSecurity and composition of multiparty cryptographic protocols,\u201d J. Cryptol., vol.13, no.1, pp.143-202, 2000. 10.1007\/s001459910006","DOI":"10.1007\/s001459910006"},{"key":"33","doi-asserted-by":"crossref","unstructured":"[35] R. Canetti, \u201cUniversally composable security: A new paradigm for cryptographic protocols,\u201d Proc. FOCS 2001, pp.136-145, IEEE, 2001. 10.1109\/sfcs.2001.959888","DOI":"10.1109\/SFCS.2001.959888"},{"key":"34","doi-asserted-by":"publisher","unstructured":"[36] E. Kushilevitz, Y. Lindell, and T. Rabin, \u201cInformation-theoretically secure protocols and security under composition,\u201d SIAM J. Comput., vol.39, no.5, pp.2090-2112, 2010. 10.1137\/090755886","DOI":"10.1137\/090755886"},{"key":"35","doi-asserted-by":"crossref","unstructured":"[37] T. Araki, J. Furukawa, Y. Lindell, A. Nof, and K. Ohara, \u201cHigh-throughput semi-honest secure three-party computation with an honest majority,\u201d Proc. CCS 2016, pp.805-817, 2016. 10.1145\/2976749.2978331","DOI":"10.1145\/2976749.2978331"},{"key":"36","doi-asserted-by":"crossref","unstructured":"[38] D. Demmler, T. Schneider, and M. Zohner, \u201cABY-A framework for efficient mixed-protocol secure two-party computation,\u201d Proc. NDSS 2015, Internet Society, 2015. 10.14722\/ndss.2015.23113","DOI":"10.14722\/ndss.2015.23113"},{"key":"37","unstructured":"[39] S. Ioffe and C. Szegedy, \u201cBatch normalization: Accelerating deep network training by reducing internal covariate shift,\u201d Proc. IML 2015, pp.448-456, JMLR.org, 2015."},{"key":"38","unstructured":"[40] M.S. Riazi, M. Samragh, H. Chen, K. Laine, K. Lauter, and F. Koushanfar, \u201cXONN: XNOR-based oblivious deep neural network inference,\u201d Proc. Usenix Security 2019, pp.1501-1518, Usenix Association, 2019."},{"key":"39","doi-asserted-by":"crossref","unstructured":"[41] I. Damgard, M. Fitzi, E. Kiltz, J.B. Nielsen, and T. Toft, \u201cUnconditionally secure constant-rounds multi-party computation for equality, comparison, bits and exponentiation,\u201d Proc. TCC 2006, LNCS, vol.3876, pp.285-304, Springer, 2006. 10.1007\/11681878_15","DOI":"10.1007\/11681878_15"},{"key":"40","doi-asserted-by":"crossref","unstructured":"[42] K. Chida, D. Genkin, K. Hamada, D. Ikarashi, R. Kikuchi, Y. Lindell, and A. Nof, \u201cFast large-scale honest-majority MPC for malicious adversaries,\u201d Proc. CRYPTO 2018, LNCS, vol.10993, pp.34-64, 2018. 10.1007\/978-3-319-96878-0_2","DOI":"10.1007\/978-3-319-96878-0_2"}],"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\/E103.A\/12\/E103.A_2020TAP0011\/_pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,1]],"date-time":"2022-12-01T12:45:18Z","timestamp":1669898718000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.jstage.jst.go.jp\/article\/transfun\/E103.A\/12\/E103.A_2020TAP0011\/_article"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,12,1]]},"references-count":40,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2020]]}},"URL":"https:\/\/doi.org\/10.1587\/transfun.2020tap0011","relation":{},"ISSN":["0916-8508","1745-1337"],"issn-type":[{"value":"0916-8508","type":"print"},{"value":"1745-1337","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020,12,1]]}}}