{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T12:07:35Z","timestamp":1777550855029,"version":"3.51.4"},"reference-count":133,"publisher":"Privacy Enhancing Technologies Symposium Advisory Board","issue":"2","license":[{"start":{"date-parts":[[2021,1,29]],"date-time":"2021-01-29T00:00:00Z","timestamp":1611878400000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/creativecommons.org\/licenses\/by-nc-nd\/3.0"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2021,4,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>In this paper, we address the problem of privacy-preserving distributed learning and the evaluation of machine-learning models by analyzing it in the widespread MapReduce abstraction that we extend with privacy constraints. We design<jats:sc>spindle<\/jats:sc>(Scalable Privacy-preservINg Distributed LEarning), the first distributed and privacy-preserving system that covers the complete ML workflow by enabling the execution of a cooperative gradient-descent and the evaluation of the obtained model and by preserving data and model confidentiality in a passive-adversary model with up to N \u22121 colluding parties.<jats:sc>spindle<\/jats:sc>uses multiparty homomorphic encryption to execute parallel high-depth computations on encrypted data without significant overhead. We instantiate<jats:sc>spindle<\/jats:sc>for the training and evaluation of generalized linear models on distributed datasets and show that it is able to accurately (on par with non-secure centrally-trained models) and efficiently (due to a multi-level parallelization of the computations) train models that require a high number of iterations on large input data with thousands of features, distributed among hundreds of data providers. For instance, it trains a logistic-regression model on a dataset of one million samples with 32 features distributed among 160 data providers in less than three minutes.<\/jats:p>","DOI":"10.2478\/popets-2021-0030","type":"journal-article","created":{"date-parts":[[2021,4,6]],"date-time":"2021-04-06T21:03:38Z","timestamp":1617743018000},"page":"323-347","source":"Crossref","is-referenced-by-count":51,"title":["Scalable Privacy-Preserving Distributed Learning"],"prefix":"10.56553","volume":"2021","author":[{"given":"David","family":"Froelicher","sequence":"first","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]},{"given":"Juan R.","family":"Troncoso-Pastoriza","sequence":"additional","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]},{"given":"Apostolos","family":"Pyrgelis","sequence":"additional","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]},{"given":"Sinem","family":"Sav","sequence":"additional","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]},{"given":"Joao Sa","family":"Sousa","sequence":"additional","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]},{"given":"Jean-Philippe","family":"Bossuat","sequence":"additional","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]},{"given":"Jean-Pierre","family":"Hubaux","sequence":"additional","affiliation":[{"name":"Laboratory for Data Security (LDS) , EPFL"}]}],"member":"35752","published-online":{"date-parts":[[2021,1,29]]},"reference":[{"key":"2022050119080253475_j_popets-2021-0030_ref_001_w2aab3b7c34b1b6b1ab1ab1Aa","unstructured":"[1] M. Abadi et al. TensorFlow: Large-scale machine learning on heterogeneous systems, 2015. Software available from tensorflow.org."},{"key":"2022050119080253475_j_popets-2021-0030_ref_002_w2aab3b7c34b1b6b1ab1ab2Aa","doi-asserted-by":"crossref","unstructured":"[2] M. Abadi et al. Deep learning with differential privacy. In ACM CCS, 2016.10.1145\/2976749.2978318","DOI":"10.1145\/2976749.2978318"},{"key":"2022050119080253475_j_popets-2021-0030_ref_003_w2aab3b7c34b1b6b1ab1ab3Aa","doi-asserted-by":"crossref","unstructured":"[3] A. Akavia, H. Shaul, M. Weiss, and Z. Yakhini. Linear-Regression on Packed Encrypted Data in the Two-Server Model. In ACM WAHC, 2019.10.1145\/3338469.3358942","DOI":"10.1145\/3338469.3358942"},{"key":"2022050119080253475_j_popets-2021-0030_ref_004_w2aab3b7c34b1b6b1ab1ab4Aa","unstructured":"[4] M. Albrecht et al. Homomorphic Encryption Security Standard. Technical report, HomomorphicEncryption.org, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_005_w2aab3b7c34b1b6b1ab1ab5Aa","doi-asserted-by":"crossref","unstructured":"[5] M. R. Albrecht, R. Player, and S. Scott. On the concrete hardness of learning with errors. J. of Mathematical Cryptology, 2015.10.1515\/jmc-2015-0016","DOI":"10.1515\/jmc-2015-0016"},{"key":"2022050119080253475_j_popets-2021-0030_ref_006_w2aab3b7c34b1b6b1ab1ab6Aa","doi-asserted-by":"crossref","unstructured":"[6] S. V. Algesheimer J., Camenisch J. Efficient computation modulo a shared secret with application to the generation of shared safe-prime products. In CRYPTO, 2002.10.1007\/3-540-45708-9_27","DOI":"10.1007\/3-540-45708-9_27"},{"key":"2022050119080253475_j_popets-2021-0030_ref_007_w2aab3b7c34b1b6b1ab1ab7Aa","doi-asserted-by":"crossref","unstructured":"[7] Y. Aono, T. Hayashi, L. Trieu Phong, and L. Wang. Scalable and secure logistic regression via homomorphic encryption. In ACM CODASPY, 2016.10.1145\/2857705.2857731","DOI":"10.1145\/2857705.2857731"},{"key":"2022050119080253475_j_popets-2021-0030_ref_008_w2aab3b7c34b1b6b1ab1ab8Aa","unstructured":"[8] C. Baum, I. Damg\u00e5rd, S. Oechsner, and C. Peikert. Efficient commitments and zero-knowledge protocols from ring-sis with applications to lattice-based threshold cryptosystems. IACR Cryptol. ePrint Arch., 2016."},{"key":"2022050119080253475_j_popets-2021-0030_ref_009_w2aab3b7c34b1b6b1ab1ab9Aa","doi-asserted-by":"crossref","unstructured":"[9] C. Baum and A. Nof. Concretely-efficient zero-knowledge arguments for arithmetic circuits and their application to lattice-based cryptography. In PKC, 2020.10.1007\/978-3-030-45374-9_17","DOI":"10.1007\/978-3-030-45374-9_17"},{"key":"2022050119080253475_j_popets-2021-0030_ref_010_w2aab3b7c34b1b6b1ab1ac10Aa","unstructured":"[10] Breast Cancer Wisconsin (Original). https:\/\/archive.ics.uci.edu\/ml\/datasets\/breast+cancer+wisconsin+(original), (14.02.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_011_w2aab3b7c34b1b6b1ab1ac11Aa","doi-asserted-by":"crossref","unstructured":"[11] A. L. Beam and I. S. Kohane. Big data and machine learning in health care. Jama, 2018.10.1001\/jama.2017.1839129532063","DOI":"10.1001\/jama.2017.18391"},{"key":"2022050119080253475_j_popets-2021-0030_ref_012_w2aab3b7c34b1b6b1ab1ac12Aa","doi-asserted-by":"crossref","unstructured":"[12] F. Boemer, A. Costache, R. Cammarota, and C. Wierzynski. nGraph-HE2: A High-Throughput Framework for Neural Network Inference on Encrypted Data. In ACM WAHC, 2019.10.1145\/3338469.3358944","DOI":"10.1145\/3338469.3358944"},{"key":"2022050119080253475_j_popets-2021-0030_ref_013_w2aab3b7c34b1b6b1ab1ac13Aa","unstructured":"[13] D. Bogdanov, L. Kamm, S. Laur, and V. Sokk. Rmind: a tool for cryptographically secure statistical analysis. IEEE TDSC, 2016."},{"key":"2022050119080253475_j_popets-2021-0030_ref_014_w2aab3b7c34b1b6b1ab1ac14Aa","unstructured":"[14] K. Bonawitz et al. Towards federated learning at scale: System design. In SysML, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_015_w2aab3b7c34b1b6b1ab1ac15Aa","doi-asserted-by":"crossref","unstructured":"[15] C. Bonte and F. Vercauteren. Privacy-preserving logistic regression training. BMC medical genomics, 2018.10.1186\/s12920-018-0398-y618035730309364","DOI":"10.1186\/s12920-018-0398-y"},{"key":"2022050119080253475_j_popets-2021-0030_ref_016_w2aab3b7c34b1b6b1ab1ac16Aa","doi-asserted-by":"crossref","unstructured":"[16] J. W. Bos, K. Lauter, J. Loftus, and M. Naehrig. Improved security for a ring-based fully homomorphic encryption scheme. In IMACC, 2013.10.1007\/978-3-642-45239-0_4","DOI":"10.1007\/978-3-642-45239-0_4"},{"key":"2022050119080253475_j_popets-2021-0030_ref_017_w2aab3b7c34b1b6b1ab1ac17Aa","doi-asserted-by":"crossref","unstructured":"[17] R. Bost, R. A. Popa, S. Tu, and S. Goldwasser. Machine learning classification over encrypted data. In NDSS, 2015.10.14722\/ndss.2015.23241","DOI":"10.14722\/ndss.2015.23241"},{"key":"2022050119080253475_j_popets-2021-0030_ref_018_w2aab3b7c34b1b6b1ab1ac18Aa","doi-asserted-by":"crossref","unstructured":"[18] L. Bottou, F. E. Curtis, and J. Nocedal. Optimization methods for large-scale machine learning. Siam Review, 2018.10.1137\/16M1080173","DOI":"10.1137\/16M1080173"},{"key":"2022050119080253475_j_popets-2021-0030_ref_019_w2aab3b7c34b1b6b1ab1ac19Aa","doi-asserted-by":"crossref","unstructured":"[19] S. Boyd, N. Parikh, E. Chu, B. Peleato, J. Eckstein, et al. Distributed optimization and statistical learning via the alternating direction method of multipliers. Foundations and Trends in Machine learning, 2011.10.1561\/9781601984616","DOI":"10.1561\/9781601984616"},{"key":"2022050119080253475_j_popets-2021-0030_ref_020_w2aab3b7c34b1b6b1ab1ac20Aa","unstructured":"[20] CalCOFI, over 60 years of oceanographic data. https:\/\/www.kaggle.com\/sohier\/calcofi, (05.03.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_021_w2aab3b7c34b1b6b1ab1ac21Aa","doi-asserted-by":"crossref","unstructured":"[21] S. Carpov, N. Gama, M. Georgieva, and J. R. Troncoso-Pastoriza. Privacy-preserving semi-parallel logistic regression training with fully homomorphic encryption. IACR Cryptology ePrint Archive, 2019.10.1186\/s12920-020-0723-0737276532693814","DOI":"10.1186\/s12920-020-0723-0"},{"key":"2022050119080253475_j_popets-2021-0030_ref_022_w2aab3b7c34b1b6b1ab1ac22Aa","unstructured":"[22] K. Chaudhuri and C. Monteleoni. Privacy-preserving logistic regression. In NIPS, 2009."},{"key":"2022050119080253475_j_popets-2021-0030_ref_023_w2aab3b7c34b1b6b1ab1ac23Aa","doi-asserted-by":"crossref","unstructured":"[23] H. Chen, R. Gilad-Bachrach, K. Han, Z. Huang, A. Jalali, K. Laine, and K. Lauter. Logistic regression over encrypted data from fully homomorphic encryption. BMC medical genomics, 2018.10.1186\/s12920-018-0397-z618040230309350","DOI":"10.1186\/s12920-018-0397-z"},{"key":"2022050119080253475_j_popets-2021-0030_ref_024_w2aab3b7c34b1b6b1ab1ac24Aa","doi-asserted-by":"crossref","unstructured":"[24] J. H. Cheon, M. Hhan, S. Hong, and Y. Son. A hybrid of dual and meet-in-the-middle attack on sparse and ternary secret LWE. IEEE Access, 2019.10.1109\/ACCESS.2019.2925425","DOI":"10.1109\/ACCESS.2019.2925425"},{"key":"2022050119080253475_j_popets-2021-0030_ref_025_w2aab3b7c34b1b6b1ab1ac25Aa","doi-asserted-by":"crossref","unstructured":"[25] J. H. Cheon, A. Kim, M. Kim, and Y. Song. Homomorphic encryption for arithmetic of approximate numbers. In ASIACRYPT, 2017.10.1007\/978-3-319-70694-8_15","DOI":"10.1007\/978-3-319-70694-8_15"},{"key":"2022050119080253475_j_popets-2021-0030_ref_026_w2aab3b7c34b1b6b1ab1ac26Aa","doi-asserted-by":"crossref","unstructured":"[26] H. Cho, D. Wu, and B. Berger. Secure genome-wide association analysis using multiparty computation. Nature Biotech., 2018.10.1038\/nbt.4108599044029734293","DOI":"10.1038\/nbt.4108"},{"key":"2022050119080253475_j_popets-2021-0030_ref_027_w2aab3b7c34b1b6b1ab1ac27Aa","doi-asserted-by":"crossref","unstructured":"[27] C.-T. Chu et al. Map-reduce for machine learning on multi-core. In NIPS, 2007.","DOI":"10.7551\/mitpress\/7503.003.0040"},{"key":"2022050119080253475_j_popets-2021-0030_ref_028_w2aab3b7c34b1b6b1ab1ac28Aa","unstructured":"[28] H. Corrigan-Gibbs and D. Boneh. Prio: Private, Robust, and Computation of Aggregate Statistics. In NSDI, 2017."},{"key":"2022050119080253475_j_popets-2021-0030_ref_029_w2aab3b7c34b1b6b1ab1ac29Aa","doi-asserted-by":"crossref","unstructured":"[29] J. L. Crawford, C. Gentry, S. Halevi, D. Platt, and V. Shoup. Doing real work with FHE: The case of logistic regression. In ACM WAHC, 2018.10.1145\/3267973.3267974","DOI":"10.1145\/3267973.3267974"},{"key":"2022050119080253475_j_popets-2021-0030_ref_030_w2aab3b7c34b1b6b1ab1ac30Aa","doi-asserted-by":"crossref","unstructured":"[30] I. Damg\u00e5rd, V. Pastro, N. Smart, and S. Zakarias. Multi-party computation from somewhat homomorphic encryption. In CRYPTO, 2012.10.1007\/978-3-642-32009-5_38","DOI":"10.1007\/978-3-642-32009-5_38"},{"key":"2022050119080253475_j_popets-2021-0030_ref_031_w2aab3b7c34b1b6b1ab1ac31Aa","doi-asserted-by":"crossref","unstructured":"[31] J. Dean and S. Ghemawat. MapReduce: simplified data processing on large clusters. Communications of the ACM, 2008.10.1145\/1327452.1327492","DOI":"10.1145\/1327452.1327492"},{"key":"2022050119080253475_j_popets-2021-0030_ref_032_w2aab3b7c34b1b6b1ab1ac32Aa","unstructured":"[32] S. S. Du, J. D. Lee, H. Li, L. Wang, and X. Zhai. Gradient descent finds global minima of deep neural networks. CoRR, abs\/1811.03804, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_033_w2aab3b7c34b1b6b1ab1ac33Aa","unstructured":"[33] S. S. Du, X. Zhai, B. Poczos, and A. Singh. Gradient descent provably optimizes over-parameterized neural networks. arXiv preprint arXiv:1810.02054, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_034_w2aab3b7c34b1b6b1ab1ac34Aa","doi-asserted-by":"crossref","unstructured":"[34] W. Du, A. Li, and Q. Li. Privacy-Preserving Multiparty Learning For Logistic Regression. In SecureComm, 2018.10.1007\/978-3-030-01701-9_30","DOI":"10.1007\/978-3-030-01701-9_30"},{"key":"2022050119080253475_j_popets-2021-0030_ref_035_w2aab3b7c34b1b6b1ab1ac35Aa","doi-asserted-by":"crossref","unstructured":"[35] T. ElGamal. A public key cryptosystem and a signature scheme based on discrete logarithms. IEEE Trans-IT, 1985.10.1109\/TIT.1985.1057074","DOI":"10.1109\/TIT.1985.1057074"},{"key":"2022050119080253475_j_popets-2021-0030_ref_036_w2aab3b7c34b1b6b1ab1ac36Aa","doi-asserted-by":"crossref","unstructured":"[36] B. J. Erickson, P. Korfiatis, Z. Akkus, and T. L. Kline. Machine learning for medical imaging. Radiographics, 2017.10.1148\/rg.2017160130537562128212054","DOI":"10.1148\/rg.2017160130"},{"key":"2022050119080253475_j_popets-2021-0030_ref_037_w2aab3b7c34b1b6b1ab1ac37Aa","unstructured":"[37] Epileptic Seizure Recognition Dataset. https:\/\/archive.ics.uci.edu\/ml\/datasets\/Epileptic+Seizure+Recognition, (14.02.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_038_w2aab3b7c34b1b6b1ab1ac38Aa","unstructured":"[38] J. Fan and F. Vercauteren. Somewhat practical fully homomorphic encryption. IACR Cryptology ePrint Archive, 2012."},{"key":"2022050119080253475_j_popets-2021-0030_ref_039_w2aab3b7c34b1b6b1ab1ac39Aa","doi-asserted-by":"crossref","unstructured":"[39] M. Fredrikson, S. Jha, and T. Ristenpart. Model inversion attacks that exploit confidence information and basic countermeasures. In ACM CCS, 2015.10.1145\/2810103.2813677","DOI":"10.1145\/2810103.2813677"},{"key":"2022050119080253475_j_popets-2021-0030_ref_040_w2aab3b7c34b1b6b1ab1ac40Aa","doi-asserted-by":"crossref","unstructured":"[40] D. Froelicher, P. Egger, J. S. Sousa, J. L. Raisaro, Z. Huang, C. V. Mouchet, B. Ford, and J.-P. Hubaux. Unlynx: A decentralized system for privacy-conscious data sharing. PETS, 2017.10.1515\/popets-2017-0047","DOI":"10.1515\/popets-2017-0047"},{"key":"2022050119080253475_j_popets-2021-0030_ref_041_w2aab3b7c34b1b6b1ab1ac41Aa","doi-asserted-by":"crossref","unstructured":"[41] D. Froelicher, J. R. Troncoso-Pastoriza, J. S. Sousa, and J. Hubaux. Drynx: Decentralized, secure, verifiable system for statistical queries and machine learning on distributed datasets. IEEE TIFS, 2020.10.1109\/TIFS.2020.2976612","DOI":"10.1109\/TIFS.2020.2976612"},{"key":"2022050119080253475_j_popets-2021-0030_ref_042_w2aab3b7c34b1b6b1ab1ac42Aa","doi-asserted-by":"crossref","unstructured":"[42] A. Gasc\u00f3n, P. Schoppmann, B. Balle, M. Raykova, J. Doerner, S. Zahur, and D. Evans. Privacy-preserving distributed linear regression on high-dimensional data. PETS, 2017.10.1515\/popets-2017-0053","DOI":"10.1515\/popets-2017-0053"},{"key":"2022050119080253475_j_popets-2021-0030_ref_043_w2aab3b7c34b1b6b1ab1ac43Aa","unstructured":"[43] The EU General Data Protection Regulation. https:\/\/gdprinfo.eu\/, (15.12.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_044_w2aab3b7c34b1b6b1ab1ac44Aa","doi-asserted-by":"crossref","unstructured":"[44] I. Giacomelli, S. Jha, M. Joye, C. D. Page, and K. Yoon. Privacy-preserving ridge regression with only linearly-homomorphic encryption. In ACNS, 2018.10.1007\/978-3-319-93387-0_13","DOI":"10.1007\/978-3-319-93387-0_13"},{"key":"2022050119080253475_j_popets-2021-0030_ref_045_w2aab3b7c34b1b6b1ab1ac45Aa","unstructured":"[45] R. Gilad-Bachrach, N. Dowlin, K. Laine, K. Lauter, M. Naehrig, and J. Wernsing. Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy. In ICML, 2016."},{"key":"2022050119080253475_j_popets-2021-0030_ref_046_w2aab3b7c34b1b6b1ab1ac46Aa","unstructured":"[46] Go Programming Language. https:\/\/golang.org, (10.11.2019)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_047_w2aab3b7c34b1b6b1ab1ac47Aa","doi-asserted-by":"crossref","unstructured":"[47] L. Gomes. Quantum computing: Both here and not here. IEEE Spectrum, 2018.10.1109\/MSPEC.2018.8322045","DOI":"10.1109\/MSPEC.2018.8322045"},{"key":"2022050119080253475_j_popets-2021-0030_ref_048_w2aab3b7c34b1b6b1ab1ac48Aa","unstructured":"[48] I. Goodfellow, Y. Bengio, and A. Courville. Deep Learning. MIT Press, 2016. http:\/\/www.deeplearningbook.org."},{"key":"2022050119080253475_j_popets-2021-0030_ref_049_w2aab3b7c34b1b6b1ab1ac49Aa","unstructured":"[49] Google CEO Sundar Pichai on achieving quantum supremacy. https:\/\/tinyurl.com\/y5rnowlc, (07.11.2019)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_050_w2aab3b7c34b1b6b1ab1ac50Aa","doi-asserted-by":"crossref","unstructured":"[50] T. Graepel, K. Lauter, and M. Naehrig. ML confidential: Machine learning on encrypted data. In ICISC, 2012.10.1007\/978-3-642-37682-5_1","DOI":"10.1007\/978-3-642-37682-5_1"},{"key":"2022050119080253475_j_popets-2021-0030_ref_051_w2aab3b7c34b1b6b1ab1ac51Aa","doi-asserted-by":"crossref","unstructured":"[51] S. Halevi and V. Shoup. Algorithms in HElib. In CRYPTO, 2014.10.1007\/978-3-662-44371-2_31","DOI":"10.1007\/978-3-662-44371-2_31"},{"key":"2022050119080253475_j_popets-2021-0030_ref_052_w2aab3b7c34b1b6b1ab1ac52Aa","doi-asserted-by":"crossref","unstructured":"[52] K. Han and D. Ki. Better bootstrapping for approximate homomorphic encryption. In CT-RSA, 2020.10.1007\/978-3-030-40186-3_16","DOI":"10.1007\/978-3-030-40186-3_16"},{"key":"2022050119080253475_j_popets-2021-0030_ref_053_w2aab3b7c34b1b6b1ab1ac53Aa","doi-asserted-by":"crossref","unstructured":"[53] E. Hesamifard, H. Takabi, M. Ghasemi, and R. N. Wright. Privacy-preserving machine learning as a service. PETS, 2018.10.1515\/popets-2018-0024","DOI":"10.1515\/popets-2018-0024"},{"key":"2022050119080253475_j_popets-2021-0030_ref_054_w2aab3b7c34b1b6b1ab1ac54Aa","doi-asserted-by":"crossref","unstructured":"[54] B. Hitaj, G. Ateniese, and F. Perez-Cruz. Deep models under the GAN: information leakage from collaborative deep learning. In ACM CCS, 2017.10.1145\/3133956.3134012","DOI":"10.1145\/3133956.3134012"},{"key":"2022050119080253475_j_popets-2021-0030_ref_055_w2aab3b7c34b1b6b1ab1ac55Aa","doi-asserted-by":"crossref","unstructured":"[55] Z. Huang, R. Hu, Y. Guo, E. Chan-Tin, and Y. Gong. DPADMM: ADMM-based distributed learning with differential privacy. IEEE TIFS, 2019.10.1109\/TIFS.2019.2931068","DOI":"10.1109\/TIFS.2019.2931068"},{"key":"2022050119080253475_j_popets-2021-0030_ref_056_w2aab3b7c34b1b6b1ab1ac56Aa","unstructured":"[56] Quantum Computing is \u201cno longer science fiction,\u201d says IBM. https:\/\/tinyurl.com\/y4zvlsll, (10.02.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_057_w2aab3b7c34b1b6b1ab1ac57Aa","doi-asserted-by":"crossref","unstructured":"[57] K. A. Jagadeesh, D. J. Wu, J. A. Birgmeier, D. Boneh, and G. Bejerano. Deriving genomic diagnoses without revealing patient genomes. Science, 2017.10.1126\/science.aam971028818945","DOI":"10.1126\/science.aam9710"},{"key":"2022050119080253475_j_popets-2021-0030_ref_058_w2aab3b7c34b1b6b1ab1ac58Aa","unstructured":"[58] B. Jayaraman and D. Evans. Evaluating differentially private machine learning in practice. In USENIX Security, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_059_w2aab3b7c34b1b6b1ab1ac59Aa","unstructured":"[59] B. Jayaraman, L. Wang, D. Evans, and Q. Gu. Distributed learning without distress: Privacy-preserving empirical risk minimization. In NIPS, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_060_w2aab3b7c34b1b6b1ab1ac60Aa","doi-asserted-by":"crossref","unstructured":"[60] Y. Jiang et al. SecureLR: Secure logistic regression model via a hybrid cryptographic protocol. IEEE TCB, 2019.10.1109\/TCBB.2018.283346329994005","DOI":"10.1109\/TCBB.2018.2833463"},{"key":"2022050119080253475_j_popets-2021-0030_ref_061_w2aab3b7c34b1b6b1ab1ac61Aa","unstructured":"[61] C. Juvekar, V. Vaikuntanathan, and A. Chandrakasan. GAZELLE: A low latency framework for secure neural network inference. In USENIX Security, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_062_w2aab3b7c34b1b6b1ab1ac62Aa","unstructured":"[62] Why we shouldn\u2019t disregard the nda. tinyurl.com\/y4hdr42d,, (05.03.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_063_w2aab3b7c34b1b6b1ab1ac63Aa","doi-asserted-by":"crossref","unstructured":"[63] A. Kim, Y. Song, M. Kim, K. Lee, and J. H. Cheon. Logistic regression model training based on the approximate homomorphic encryption. BMC genomics, 2018.10.1186\/s12920-018-0401-7618036730309349","DOI":"10.1186\/s12920-018-0401-7"},{"key":"2022050119080253475_j_popets-2021-0030_ref_064_w2aab3b7c34b1b6b1ab1ac64Aa","doi-asserted-by":"crossref","unstructured":"[64] M. Kim, J. Lee, L. Ohno-Machado, and X. Jiang. Secure and differentially private logistic regression for horizontally distributed data. IEEE TIFS, 2019.10.1109\/TIFS.2019.2925496","DOI":"10.1109\/TIFS.2019.2925496"},{"key":"2022050119080253475_j_popets-2021-0030_ref_065_w2aab3b7c34b1b6b1ab1ac65Aa","doi-asserted-by":"crossref","unstructured":"[65] M. Kim, J. Lee, L. Ohno-Machado, and X. Jiang. Secure and differentially private logistic regression for horizontally distributed data. IEEE TIFS, 2020.10.1109\/TIFS.2019.2925496","DOI":"10.1109\/TIFS.2019.2925496"},{"key":"2022050119080253475_j_popets-2021-0030_ref_066_w2aab3b7c34b1b6b1ab1ac66Aa","doi-asserted-by":"crossref","unstructured":"[66] M. Kim, Y. Song, S. Wang, Y. Xia, and X. Jiang. Secure logistic regression based on homomorphic encryption: Design and evaluation. JMIR medical informatics, 2018.10.2196\/preprints.8805","DOI":"10.2196\/preprints.8805"},{"key":"2022050119080253475_j_popets-2021-0030_ref_067_w2aab3b7c34b1b6b1ab1ac67Aa","unstructured":"[67] A. Koloskova, S. U. Stich, and M. Jaggi. Decentralized stochastic optimization and gossip algorithms with compressed communication. CoRR, abs\/1902.00340, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_068_w2aab3b7c34b1b6b1ab1ac68Aa","unstructured":"[68] J. Kone\u010dn\u00fd, H. McMahan, D. Ramage, and P. Richt\u00e1rik. Federated optimization: Distributed machine learning for on-device intelligence. arXiv preprint arXiv:1610.02527, 2016."},{"key":"2022050119080253475_j_popets-2021-0030_ref_069_w2aab3b7c34b1b6b1ab1ac69Aa","doi-asserted-by":"crossref","unstructured":"[69] A. Kumar, J. Naughton, and J. M. Patel. Learning generalized linear models over normalized data. In ACM SIGMOD, 2015.10.1145\/2723372.2723713","DOI":"10.1145\/2723372.2723713"},{"key":"2022050119080253475_j_popets-2021-0030_ref_070_w2aab3b7c34b1b6b1ab1ac70Aa","unstructured":"[70] Y. LeCun and C. Cortes. MNIST handwritten digit database. http:\/\/yann.lecun.com\/exdb\/mnist\/, 2010."},{"key":"2022050119080253475_j_popets-2021-0030_ref_071_w2aab3b7c34b1b6b1ab1ac71Aa","doi-asserted-by":"crossref","unstructured":"[71] M. K. Leung, A. Delong, B. Alipanahi, and B. J. Frey. Machine learning in genomic medicine: a review of computational problems and data sets. Proceedings of the IEEE, 2015.10.1109\/JPROC.2015.2494198","DOI":"10.1109\/JPROC.2015.2494198"},{"key":"2022050119080253475_j_popets-2021-0030_ref_072_w2aab3b7c34b1b6b1ab1ac72Aa","doi-asserted-by":"crossref","unstructured":"[72] W. Li et al. Privacy-preserving federated brain tumour segmentation. In MLMI, 2019.10.1007\/978-3-030-32692-0_16","DOI":"10.1007\/978-3-030-32692-0_16"},{"key":"2022050119080253475_j_popets-2021-0030_ref_073_w2aab3b7c34b1b6b1ab1ac73Aa","doi-asserted-by":"crossref","unstructured":"[73] B. Libert, S. Ling, K. Nguyen, and H. Wang. Lattice-based zero-knowledge arguments for integer relations. In CRYPTO, 2018.10.1007\/978-3-319-96881-0_24","DOI":"10.1007\/978-3-319-96881-0_24"},{"key":"2022050119080253475_j_popets-2021-0030_ref_074_w2aab3b7c34b1b6b1ab1ac74Aa","doi-asserted-by":"crossref","unstructured":"[74] Y. Lindell. How to simulate it\u2013a tutorial on the simulation proof technique. In Tutorials on the Foundations of Cryptography. 2017.10.1007\/978-3-319-57048-8_6","DOI":"10.1007\/978-3-319-57048-8_6"},{"key":"2022050119080253475_j_popets-2021-0030_ref_075_w2aab3b7c34b1b6b1ab1ac75Aa","doi-asserted-by":"crossref","unstructured":"[75] R. Lindner and C. Peikert. Better key sizes (and attacks) for LWE-based encryption. In CT-RSA, 2011.10.1007\/978-3-642-19074-2_21","DOI":"10.1007\/978-3-642-19074-2_21"},{"key":"2022050119080253475_j_popets-2021-0030_ref_076_w2aab3b7c34b1b6b1ab1ac76Aa","unstructured":"[76] J. K. Lindsey. Applying generalized linear models. Springer Science & Business Media, 2000."},{"key":"2022050119080253475_j_popets-2021-0030_ref_077_w2aab3b7c34b1b6b1ab1ac77Aa","unstructured":"[77] Why NDAs often don\u2019t work when expected to do so and what to do about it. https:\/\/tinyurl.com\/y64qlzs9,, (05.03.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_078_w2aab3b7c34b1b6b1ab1ac78Aa","doi-asserted-by":"crossref","unstructured":"[78] J. Liu, M. Juuti, Y. Lu, and N. Asokan. Oblivious neural network predictions via minionn transformations. In ACM CCS, 2017.10.1145\/3133956.3134056","DOI":"10.1145\/3133956.3134056"},{"key":"2022050119080253475_j_popets-2021-0030_ref_079_w2aab3b7c34b1b6b1ab1ac79Aa","doi-asserted-by":"crossref","unstructured":"[79] V. Lyubashevsky, N. K. Nguyen, and G. Seiler. Practical lattice-based zero-knowledge proofs for integer relations. In ACM CCS, 2020.10.1145\/3372297.3417894","DOI":"10.1145\/3372297.3417894"},{"key":"2022050119080253475_j_popets-2021-0030_ref_080_w2aab3b7c34b1b6b1ab1ac80Aa","doi-asserted-by":"crossref","unstructured":"[80] V. Lyubashevsky, C. Peikert, and O. Regev. On ideal lattices and learning with errors over rings. In EUROCRYPT, 2010.10.1007\/978-3-642-13190-5_1","DOI":"10.1007\/978-3-642-13190-5_1"},{"key":"2022050119080253475_j_popets-2021-0030_ref_081_w2aab3b7c34b1b6b1ab1ac81Aa","unstructured":"[81] H. B. McMahan, E. Moore, D. Ramage, S. Hampson, et al. Communication-efficient learning of deep networks from decentralized data. arXiv preprint arXiv:1602.05629, 2016."},{"key":"2022050119080253475_j_popets-2021-0030_ref_082_w2aab3b7c34b1b6b1ab1ac82Aa","unstructured":"[82] H. B. McMahan, E. Moore, D. Ramage, and B. A. y Arcas. Federated learning of deep networks using model averaging. CoRR, abs\/1602.05629, 2016."},{"key":"2022050119080253475_j_popets-2021-0030_ref_083_w2aab3b7c34b1b6b1ab1ac83Aa","unstructured":"[83] H. B. McMahan, D. Ramage, K. Talwar, and L. Zhang. Learning differentially private recurrent language models. In ICLR, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_084_w2aab3b7c34b1b6b1ab1ac84Aa","doi-asserted-by":"crossref","unstructured":"[84] L. Melis, C. Song, E. De Cristofaro, and V. Shmatikov. Exploiting unintended feature leakage in collaborative learning. In IEEE S&P, 2019.10.1109\/SP.2019.00029","DOI":"10.1109\/SP.2019.00029"},{"key":"2022050119080253475_j_popets-2021-0030_ref_085_w2aab3b7c34b1b6b1ab1ac85Aa","unstructured":"[85] Lattigo: A library for lattice-based homomorphic encryption in go. https:\/\/github.com\/ldsec\/lattigo, (14.02.2019)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_086_w2aab3b7c34b1b6b1ab1ac86Aa","unstructured":"[86] Mininet. http:\/\/mininet.org, (13.12.2019)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_087_w2aab3b7c34b1b6b1ab1ac87Aa","unstructured":"[87] P. Mohassel and P. Rindal. ABY 3: a mixed protocol framework for machine learning. In ACM CCS, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_088_w2aab3b7c34b1b6b1ab1ac88Aa","doi-asserted-by":"crossref","unstructured":"[88] P. Mohassel and Y. Zhang. SecureML: A system for scalable privacy-preserving machine learning. In IEEE S&P, 2017.10.1109\/SP.2017.12","DOI":"10.1109\/SP.2017.12"},{"key":"2022050119080253475_j_popets-2021-0030_ref_089_w2aab3b7c34b1b6b1ab1ac89Aa","doi-asserted-by":"crossref","unstructured":"[89] M. Mosca. Cybersecurity in an era with quantum computers: Will we be ready? IEEE S&P, 2018.10.1109\/MSP.2018.3761723","DOI":"10.1109\/MSP.2018.3761723"},{"key":"2022050119080253475_j_popets-2021-0030_ref_090_w2aab3b7c34b1b6b1ab1ac90Aa","doi-asserted-by":"crossref","unstructured":"[90] M. Mostert, A. Bredenoord, M. Biesaart, and J. Delden. Big data in medical research and EU data protection law: challenges to the consent or anonymise approach. European Journal of Human Genetics, 2016.10.1038\/ejhg.2016.71507091027307115","DOI":"10.1038\/ejhg.2016.71"},{"key":"2022050119080253475_j_popets-2021-0030_ref_091_w2aab3b7c34b1b6b1ab1ac91Aa","unstructured":"[91] C. Mouchet, J. R. Troncoso-pastoriza, J.-P. Bossuat, and J. P. Hubaux. Multiparty homomorphic encryption: From theory to practice. In Tech. Report https:\/\/eprint.iacr.org\/2020\/304, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_092_w2aab3b7c34b1b6b1ab1ac92Aa","doi-asserted-by":"crossref","unstructured":"[92] M. Nasr, R. Shokri, and A. Houmansadr. Comprehensive privacy analysis of deep learning: Passive and active white-box inference attacks against centralized and federated learning. In IEEE S&P, 2019.10.1109\/SP.2019.00065","DOI":"10.1109\/SP.2019.00065"},{"key":"2022050119080253475_j_popets-2021-0030_ref_093_w2aab3b7c34b1b6b1ab1ac93Aa","doi-asserted-by":"crossref","unstructured":"[93] J. A. Nelder and R. W. M. Wedderburn. Generalized linear models. Journal of the Royal Statistical Society, 1972.10.2307\/2344614","DOI":"10.2307\/2344614"},{"key":"2022050119080253475_j_popets-2021-0030_ref_094_w2aab3b7c34b1b6b1ab1ac94Aa","doi-asserted-by":"crossref","unstructured":"[94] Y. Nesterov. Smooth minimization of non-smooth functions. Mathematical programming, 2005.10.1007\/s10107-004-0552-5","DOI":"10.1007\/s10107-004-0552-5"},{"key":"2022050119080253475_j_popets-2021-0030_ref_095_w2aab3b7c34b1b6b1ab1ac95Aa","doi-asserted-by":"crossref","unstructured":"[95] V. Nikolaenko, U. Weinsberg, S. Ioannidis, M. Joye, D. Boneh, and N. Taft. Privacy-preserving ridge regression on hundreds of millions of records. In IEEE S&P, 2013.10.1109\/SP.2013.30","DOI":"10.1109\/SP.2013.30"},{"key":"2022050119080253475_j_popets-2021-0030_ref_096_w2aab3b7c34b1b6b1ab1ac96Aa","unstructured":"[96] Cothority network library. https:\/\/github.com\/dedis\/onet, (10.11.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_097_w2aab3b7c34b1b6b1ab1ac97Aa","unstructured":"[97] P. Paillier. Public-key cryptosystems based on composite degree residuosity classes. In EUROCRYPT, 1999."},{"key":"2022050119080253475_j_popets-2021-0030_ref_098_w2aab3b7c34b1b6b1ab1ac98Aa","unstructured":"[98] A. Paszke et al. Automatic differentiation in PyTorch. 2017."},{"key":"2022050119080253475_j_popets-2021-0030_ref_099_w2aab3b7c34b1b6b1ab1ac99Aa","unstructured":"[99] M. Pathak, S. Rane, and B. Raj. Multiparty differential privacy via aggregation of locally trained classifiers. In NIPS, 2010."},{"key":"2022050119080253475_j_popets-2021-0030_ref_100_w2aab3b7c34b1b6b1ab1ad100Aa","doi-asserted-by":"crossref","unstructured":"[100] L. T. Phong, Y. Aono, T. Hayashi, L. Wang, and S. Moriai. Privacy-preserving deep learning via additively homomorphic encryption. IEEE TIFS, 2018.10.1109\/TIFS.2017.2787987","DOI":"10.1109\/TIFS.2017.2787987"},{"key":"2022050119080253475_j_popets-2021-0030_ref_101_w2aab3b7c34b1b6b1ab1ad101Aa","unstructured":"[101] Pima Indians Diabetes Dataset. https:\/\/tinyurl.com\/y8o3x8me, (14.04.2018)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_102_w2aab3b7c34b1b6b1ab1ad102Aa","unstructured":"[102] M. Pratyush, R. Lehmkuhl, A. Srinivasan, W. Zheng, and R. A. Popa. Delphi: A cryptographic inference service for neural networks. In USENIX Security, 2020."},{"key":"2022050119080253475_j_popets-2021-0030_ref_103_w2aab3b7c34b1b6b1ab1ad103Aa","unstructured":"[103] R. Rachuri and A. Suresh. Trident: Efficient 4PC framework for privacy preserving machine learning. In NDSS, 2020.10.2478\/popets-2020-0036"},{"key":"2022050119080253475_j_popets-2021-0030_ref_104_w2aab3b7c34b1b6b1ab1ad104Aa","doi-asserted-by":"crossref","unstructured":"[104] M. S. Riazi et al. Chameleon: A hybrid secure computation framework for machine learning applications. In ASIACCS, 2018.10.1145\/3196494.3196522","DOI":"10.1145\/3196494.3196522"},{"key":"2022050119080253475_j_popets-2021-0030_ref_105_w2aab3b7c34b1b6b1ab1ad105Aa","unstructured":"[105] M. S. Riazi, M. Samragh, H. Chen, K. Laine, K. E. Lauter, and F. Koushanfar. XONN: XNOR-based oblivious deep neural network inference. In USENIX Security, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_106_w2aab3b7c34b1b6b1ab1ad106Aa","doi-asserted-by":"crossref","unstructured":"[106] B. D. Rouhani, M. S. Riazi, and F. Koushanfar. Deepse-cure: Scalable provably-secure deep learning. In ACM DAC, 2018.10.1145\/3195970.3196023","DOI":"10.1145\/3195970.3196023"},{"key":"2022050119080253475_j_popets-2021-0030_ref_107_w2aab3b7c34b1b6b1ab1ad107Aa","unstructured":"[107] B. Schoenmakers and P. Tuyls. Efficient computation modulo a shared secret with application to the generation of shared safe-prime products. In EUROCRYPT, 2006."},{"key":"2022050119080253475_j_popets-2021-0030_ref_108_w2aab3b7c34b1b6b1ab1ad108Aa","doi-asserted-by":"crossref","unstructured":"[108] P. Schoppmann, A. Gascon, M. Raykova, and B. Pinkas. Make some room for the zeros: Data sparsity in secure distributed machine learning. In ACM CCS, 2019.10.1145\/3319535.3339816","DOI":"10.1145\/3319535.3339816"},{"key":"2022050119080253475_j_popets-2021-0030_ref_109_w2aab3b7c34b1b6b1ab1ad109Aa","unstructured":"[109] Scikit-learn, Machine Learning in Python. https:\/\/scikit-learn.org\/stable\/, (29.02.2020)."},{"key":"2022050119080253475_j_popets-2021-0030_ref_110_w2aab3b7c34b1b6b1ab1ad110Aa","doi-asserted-by":"crossref","unstructured":"[110] A. Shamir. How to share a secret. Communications of the ACM, 1979.10.1145\/359168.359176","DOI":"10.1145\/359168.359176"},{"key":"2022050119080253475_j_popets-2021-0030_ref_111_w2aab3b7c34b1b6b1ab1ad111Aa","doi-asserted-by":"crossref","unstructured":"[111] R. Shokri and V. Shmatikov. Privacy-preserving deep learning. In ACM CCS, 2015.10.1145\/2810103.2813687","DOI":"10.1145\/2810103.2813687"},{"key":"2022050119080253475_j_popets-2021-0030_ref_112_w2aab3b7c34b1b6b1ab1ad112Aa","doi-asserted-by":"crossref","unstructured":"[112] R. Shokri, M. Stronati, C. Song, and V. Shmatikov. Membership inference attacks against machine learning models. In IEEE S&P, 2017.10.1109\/SP.2017.41","DOI":"10.1109\/SP.2017.41"},{"key":"2022050119080253475_j_popets-2021-0030_ref_113_w2aab3b7c34b1b6b1ab1ad113Aa","unstructured":"[113] I. Stoica, D. Song, R. A. Popa, D. Patterson, M. W. Mahoney, R. Katz, A. D. Joseph, M. Jordan, J. M. Hellerstein, J. E. Gonzalez, et al. A berkeley view of systems challenges for ai. arXiv preprint arXiv:1712.05855, 2017."},{"key":"2022050119080253475_j_popets-2021-0030_ref_114_w2aab3b7c34b1b6b1ab1ad114Aa","doi-asserted-by":"crossref","unstructured":"[114] B. Terhal. Quantum supremacy, here we come. Nature Physics, 2018.10.1038\/s41567-018-0131-y","DOI":"10.1038\/s41567-018-0131-y"},{"key":"2022050119080253475_j_popets-2021-0030_ref_115_w2aab3b7c34b1b6b1ab1ad115Aa","unstructured":"[115] R. Toshniwal, K. Dastidar, and A. Nath. Big data security issues and challenges. International Journal of Innovative Research in Advanced Engineering, 2015."},{"key":"2022050119080253475_j_popets-2021-0030_ref_116_w2aab3b7c34b1b6b1ab1ad116Aa","unstructured":"[116] P. Toulis, E. Airoldi, and J. Rennie. Statistical analysis of stochastic gradient methods for generalized linear models. In ICML, 2014."},{"key":"2022050119080253475_j_popets-2021-0030_ref_117_w2aab3b7c34b1b6b1ab1ad117Aa","doi-asserted-by":"crossref","unstructured":"[117] S. Truex et al. A hybrid approach to privacy-preserving federated learning. In ACM AISec, 2019.10.1145\/3338501.3357370","DOI":"10.1145\/3338501.3357370"},{"key":"2022050119080253475_j_popets-2021-0030_ref_118_w2aab3b7c34b1b6b1ab1ad118Aa","unstructured":"[118] J. Verbraeken, M. Wolting, J. Katzy, J. Kloppenburg, T. Verbelen, and J. S. Rellermeyer. A survey on distributed machine learning. arXiv preprint arXiv:1912.09789, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_119_w2aab3b7c34b1b6b1ab1ad119Aa","doi-asserted-by":"crossref","unstructured":"[119] S. Wagh, D. Gupta, and N. Chandran. SecureNN: 3-party secure computation for neural network training. PETS, 2019.10.2478\/popets-2019-0035","DOI":"10.2478\/popets-2019-0035"},{"key":"2022050119080253475_j_popets-2021-0030_ref_120_w2aab3b7c34b1b6b1ab1ad120Aa","unstructured":"[120] J. Wang and G. Joshi. Cooperative SGD: A unified framework for the design and analysis of communication-efficient SGD algorithms. CoRR, abs\/1808.07576, 2018."},{"key":"2022050119080253475_j_popets-2021-0030_ref_121_w2aab3b7c34b1b6b1ab1ad121Aa","unstructured":"[121] J. Wang and G. Joshi. Cooperative SGD: A unified framework for the design and analysis of communication-efficient sgd algorithms. In ICML CodML Workshop, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_122_w2aab3b7c34b1b6b1ab1ad122Aa","doi-asserted-by":"crossref","unstructured":"[122] Z. Wang, M. Song, Z. Zhang, Y. Song, Q. Wang, and H. Qi. Beyond inferring class representatives: User-level privacy leakage from federated learning. In IEEE INFOCOM, 2019.10.1109\/INFOCOM.2019.8737416","DOI":"10.1109\/INFOCOM.2019.8737416"},{"key":"2022050119080253475_j_popets-2021-0030_ref_123_w2aab3b7c34b1b6b1ab1ad123Aa","unstructured":"[123] D. I. Wolinsky, H. Corrigan-Gibbs, B. Ford, and A. Johnson. Scalable anonymous group communication in the anytrust model. Technical report, Naval Research Lab Washington DC, 2012."},{"key":"2022050119080253475_j_popets-2021-0030_ref_124_w2aab3b7c34b1b6b1ab1ad124Aa","doi-asserted-by":"crossref","unstructured":"[124] R. Yang, M. H. Au, Z. Zhang, Q. Xu, Z. Yu, and W. Whyte. Efficient lattice-based zero-knowledge arguments with standard soundness: construction and applications. In CRYPTO, 2019.10.1007\/978-3-030-26948-7_6","DOI":"10.1007\/978-3-030-26948-7_6"},{"key":"2022050119080253475_j_popets-2021-0030_ref_125_w2aab3b7c34b1b6b1ab1ad125Aa","unstructured":"[125] A. C.-C. Yao. How to generate and exchange secrets. In IEEE SFCS, 1986."},{"key":"2022050119080253475_j_popets-2021-0030_ref_126_w2aab3b7c34b1b6b1ab1ad126Aa","unstructured":"[126] Yongha Son and Jung Hee Cheon. Revisiting the hybrid attack on sparse and ternary secret LWE. Technical Report https:\/\/eprint.iacr.org\/2019\/1019,, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_127_w2aab3b7c34b1b6b1ab1ad127Aa","unstructured":"[127] A. Zalcman et al. Quantum supremacy using a programmable superconducting processor. Nature, 2019."},{"key":"2022050119080253475_j_popets-2021-0030_ref_128_w2aab3b7c34b1b6b1ab1ad128Aa","doi-asserted-by":"crossref","unstructured":"[128] D. Zhang. Big data security and privacy protection. In ICMCS, 2018.10.2991\/icmcs-18.2018.56","DOI":"10.2991\/icmcs-18.2018.56"},{"key":"2022050119080253475_j_popets-2021-0030_ref_129_w2aab3b7c34b1b6b1ab1ad129Aa","unstructured":"[129] S. Zhang, A. E. Choromanska, and Y. LeCun. Deep learning with elastic averaging sgd. In NIPS, 2015."},{"key":"2022050119080253475_j_popets-2021-0030_ref_130_w2aab3b7c34b1b6b1ab1ad130Aa","doi-asserted-by":"crossref","unstructured":"[130] T. Zhang. Solving large scale linear prediction problems using stochastic gradient descent algorithms. In ICML, 2004.10.1145\/1015330.1015332","DOI":"10.1145\/1015330.1015332"},{"key":"2022050119080253475_j_popets-2021-0030_ref_131_w2aab3b7c34b1b6b1ab1ad131Aa","doi-asserted-by":"crossref","unstructured":"[131] W. Zheng, R. A. Popa, J. E. Gonzalez, and I. Stoica. Helen: Maliciously Secure Coopetitive Learning for Linear Models. In IEEE S&P, 2019.10.1109\/SP.2019.00045","DOI":"10.1109\/SP.2019.00045"},{"key":"2022050119080253475_j_popets-2021-0030_ref_132_w2aab3b7c34b1b6b1ab1ad132Aa","doi-asserted-by":"crossref","unstructured":"[132] L. Zhu, Z. Liu, and S. Han. Deep leakage from gradients. In NIPS. 2019.10.1007\/978-3-030-63076-8_2","DOI":"10.1007\/978-3-030-63076-8_2"},{"key":"2022050119080253475_j_popets-2021-0030_ref_133_w2aab3b7c34b1b6b1ab1ad133Aa","doi-asserted-by":"crossref","unstructured":"[133] X. Zhu, C. Vondrick, C. C. Fowlkes, and D. Ramanan. Do we need more training data? Int. J. Comput. Vision, 2016.10.1007\/s11263-015-0812-2","DOI":"10.1007\/s11263-015-0812-2"}],"container-title":["Proceedings on Privacy Enhancing Technologies"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.sciendo.com\/pdf\/10.2478\/popets-2021-0030","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T19:04:24Z","timestamp":1698865464000},"score":1,"resource":{"primary":{"URL":"https:\/\/petsymposium.org\/popets\/2021\/popets-2021-0030.php"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021,1,29]]},"references-count":133,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2021,1,29]]},"published-print":{"date-parts":[[2021,4,1]]}},"alternative-id":["10.2478\/popets-2021-0030"],"URL":"https:\/\/doi.org\/10.2478\/popets-2021-0030","relation":{},"ISSN":["2299-0984"],"issn-type":[{"value":"2299-0984","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021,1,29]]}}}