{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,3]],"date-time":"2026-05-03T11:03:28Z","timestamp":1777806208067,"version":"3.51.4"},"reference-count":79,"publisher":"SAGE Publications","issue":"6","content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["JCS"],"published-print":{"date-parts":[[2022,11,23]]},"abstract":"<jats:p>In this paper, we propose CryptMed, a system framework that enables medical service providers to offer secure, lightweight, and accurate medical diagnostic service to their customers via an execution of neural network inference in the ciphertext domain. CryptMed\u00a0ensures the privacy of both parties with cryptographic guarantees. Our technical contributions include: 1) presenting a secret sharing based inference protocol that can well cope with the commonly-used linear and non-linear NN layers; 2) devising optimized secure comparison function that can efficiently support comparison-based activation functions in NN architectures; 3) constructing a suite of secure smooth functions built on precise approximation approaches for accurate medical diagnoses. We evaluate CryptMed\u00a0on 6 neural network architectures across a wide range of non-linear activation functions over two benchmark and four real-world medical datasets. We comprehensively compare our system with prior art in terms of end-to-end service workload and prediction accuracy. Our empirical results demonstrate that CryptMed\u00a0achieves up to respectively 413 \u00d7, 19 \u00d7, and 43 \u00d7 bandwidth savings for MNIST, CIFAR-10, and medical applications compared with prior art. For the smooth activation based inference, the best choice of our proposed approximations preserve the precision of original functions, with less than 1.2% accuracy loss and could enhance the precision due to the newly introduced activation function family.<\/jats:p>","DOI":"10.3233\/jcs-210165","type":"journal-article","created":{"date-parts":[[2022,6,10]],"date-time":"2022-06-10T11:19:50Z","timestamp":1654859990000},"page":"795-827","source":"Crossref","is-referenced-by-count":2,"title":["Deep learning-based medical diagnostic services: A secure, lightweight, and accurate realization1"],"prefix":"10.1177","volume":"30","author":[{"given":"Xiaoning","family":"Liu","sequence":"first","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, VIC 3001, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yifeng","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xingliang","family":"Yuan","sequence":"additional","affiliation":[{"name":"Faculty of Information Technology, Monash University, Clayton, VIC 3800, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xun","family":"Yi","sequence":"additional","affiliation":[{"name":"School of Computing Technologies, RMIT University, Melbourne, VIC 3001, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"179","reference":[{"key":"10.3233\/JCS-210165_ref1","unstructured":"104th United States Congress, Health Insurance Portability and Accountability Act of 1996 (HIPPA), 1996."},{"key":"10.3233\/JCS-210165_ref2","doi-asserted-by":"crossref","unstructured":"N.\u00a0Agrawal, A.\u00a0Shahin Shamsabadi, M.J.\u00a0Kusner and A.\u00a0Gasc\u00f3n, QUOTIENT: Two-party secure neural network training and prediction, in: Proc. of ACM CCS, 2019.","DOI":"10.1145\/3319535.3339819"},{"key":"10.3233\/JCS-210165_ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-21568-2_25"},{"key":"10.3233\/JCS-210165_ref5","doi-asserted-by":"crossref","unstructured":"M.\u00a0Atallah, M.\u00a0Bykova, J.\u00a0Li, K.\u00a0Frikken and M.\u00a0Topkara, Private collaborative forecasting and benchmarking, in: Proc. of WPES, 2004.","DOI":"10.1145\/1029179.1029204"},{"key":"10.3233\/JCS-210165_ref6","doi-asserted-by":"crossref","unstructured":"P.\u00a0Baldi, R.\u00a0Baronio, E.\u00a0De Cristofaro, P.\u00a0Gasti and G.\u00a0Tsudik, Countering gattaca: Efficient and secure testing of fully-sequenced human genomes, in: Proc. of ACM CCS, 2011.","DOI":"10.1145\/2046707.2046785"},{"key":"10.3233\/JCS-210165_ref7","doi-asserted-by":"crossref","unstructured":"M.\u00a0Barni, P.\u00a0Failla, R.\u00a0Lazzeretti, A.-R.\u00a0Sadeghi and T.\u00a0Schneider, Privacy-preserving ECG classification with branching programs and neural networks, IEEE Trans. on Information Forensics and Security (2011).","DOI":"10.1109\/TIFS.2011.2108650"},{"key":"10.3233\/JCS-210165_ref8","unstructured":"D.\u00a0Beaver, Efficient multiparty protocols using circuit randomization, in: Proc. of Crypto, 1991."},{"key":"10.3233\/JCS-210165_ref9","doi-asserted-by":"crossref","unstructured":"F.\u00a0Boemer, R.\u00a0Cammarota, D.\u00a0Demmler, T.\u00a0Schneider and H.\u00a0Yalame, MP2ML: A mixed-protocol machine learning framework for private inference, in: Proceedings of the 15th International Conference on Availability, Reliability and Security, 2020, pp.\u00a01\u201310.","DOI":"10.1145\/3407023.3407045"},{"key":"10.3233\/JCS-210165_ref11","doi-asserted-by":"crossref","unstructured":"F.\u00a0Bourse, M.\u00a0Minelli, M.\u00a0Minihold and P.\u00a0Paillier, Fast homomorphic evaluation of deep discretized neural networks, in: Annual International Cryptology Conference, Springer, 2018, pp.\u00a0483\u2013512.","DOI":"10.1007\/978-3-319-96878-0_17"},{"key":"10.3233\/JCS-210165_ref12","unstructured":"A.\u00a0Brutzkus, R.\u00a0Gilad-Bachrach and O.\u00a0Elisha, Low latency privacy preserving inference, in: International Conference on Machine Learning, PMLR, 2019, pp.\u00a0812\u2013821."},{"issue":"2","key":"10.3233\/JCS-210165_ref13","doi-asserted-by":"publisher","first-page":"459","DOI":"10.2478\/popets-2020-0036","article-title":"FLASH: Fast and robust framework for privacy-preserving machine learning","volume":"2020","author":"Byali","year":"2020","journal-title":"Proc. Priv. Enhancing Technol."},{"issue":"7544","key":"10.3233\/JCS-210165_ref14","doi-asserted-by":"publisher","first-page":"400","DOI":"10.1038\/519400a","article-title":"Extreme cryptography paves way to personalized medicine","volume":"519","author":"Check Hayden","year":"2015","journal-title":"Nature News"},{"key":"10.3233\/JCS-210165_ref15","doi-asserted-by":"crossref","unstructured":"W.\u00a0Chen, Y.\u00a0Zhang, J.\u00a0He, Y.\u00a0Qiao, Y.\u00a0Chen, H.\u00a0Shi, E.X.\u00a0Wu and X.\u00a0Tang, Prostate segmentation using 2D bridged U-net, in: 2019 International Joint Conference on Neural Networks (IJCNN), IEEE, 2019, pp.\u00a01\u20137.","DOI":"10.1109\/IJCNN.2019.8851908"},{"issue":"6","key":"10.3233\/JCS-210165_ref16","doi-asserted-by":"publisher","first-page":"547","DOI":"10.1038\/nbt.4108","article-title":"Secure genome-wide association analysis using multiparty computation","volume":"36","author":"Cho","year":"2018","journal-title":"Nature Biotechnology"},{"key":"10.3233\/JCS-210165_ref17","unstructured":"D.\u00a0Clevert, T.\u00a0Unterthiner and S.\u00a0Hochreiter, Fast and accurate deep network learning by exponential linear units (ELUs), in: 4th International Conference on Learning Representations, ICLR 2016, San Juan, Puerto Rico, May 2\u20134, 2016, Conference Track Proceedings, 2016."},{"issue":"4","key":"10.3233\/JCS-210165_ref19","doi-asserted-by":"publisher","first-page":"355","DOI":"10.2478\/popets-2020-0077","article-title":"Secure evaluation of quantized neural networks","volume":"2020","author":"Dalskov","year":"2020","journal-title":"Proc. Priv. Enhancing Technol."},{"key":"10.3233\/JCS-210165_ref20","unstructured":"B.\u00a0DasGupta and G.\u00a0Schnitger, The power of approximation: A comparison of activation functions, in: NIPS, Denver, CO, 1992, pp.\u00a0615\u2013622."},{"issue":"1","key":"10.3233\/JCS-210165_ref21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1186\/1755-8794-3-1","article-title":"High performance logistic regression for privacy-preserving genome analysis","volume":"14","author":"De Cock","year":"2021","journal-title":"BMC Medical Genomics"},{"key":"10.3233\/JCS-210165_ref22","doi-asserted-by":"crossref","unstructured":"D.\u00a0Demmler, T.\u00a0Schneider and M.\u00a0Zohner, ABY \u2013 A framework for efficient mixed-protocol secure two-party computation, in: Proc. of NDSS, 2015.","DOI":"10.14722\/ndss.2015.23113"},{"key":"10.3233\/JCS-210165_ref23","unstructured":"European Parliament and the Council, The General Data Protection Regulation (GDPR), 2016."},{"key":"10.3233\/JCS-210165_ref24","doi-asserted-by":"crossref","unstructured":"M.\u00a0Fredrikson, S.\u00a0Jha and T.\u00a0Ristenpart, Model inversion attacks that exploit confidence information and basic countermeasures, in: Proc. of ACM CCS, 2015.","DOI":"10.1145\/2810103.2813677"},{"key":"10.3233\/JCS-210165_ref25","unstructured":"R.\u00a0Gilad-Bachrach, N.\u00a0Dowlin, K.\u00a0Laine, K.\u00a0Lauter, M.\u00a0Naehrig and J.\u00a0Wernsing, Cryptonets: Applying neural networks to encrypted data with high throughput and accuracy, in: Proc. of ICML, 2016."},{"key":"10.3233\/JCS-210165_ref26","doi-asserted-by":"crossref","unstructured":"O.\u00a0Goldreich, S.\u00a0Micali and A.\u00a0Wigderson, How to play any mental game or a completeness theorem for protocols with honest majority, in: Proc. of STOC, 1987.","DOI":"10.1145\/28395.28420"},{"key":"10.3233\/JCS-210165_ref28","doi-asserted-by":"crossref","unstructured":"D.\u00a0Harris, A taxonomy of parallel prefix networks, in: The Thrity-Seventh Asilomar Conference on Signals, Systems & Computers, 2003, Vol.\u00a02, IEEE, 2003, pp.\u00a02213\u20132217.","DOI":"10.1109\/ACSSC.2003.1292373"},{"issue":"6412","key":"10.3233\/JCS-210165_ref29","doi-asserted-by":"publisher","first-page":"347","DOI":"10.1126\/science.aat4807","article-title":"Realizing private and practical pharmacological collaboration","volume":"362","author":"Hie","year":"2018","journal-title":"Science"},{"issue":"2","key":"10.3233\/JCS-210165_ref30","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1016\/0893-6080(91)90009-T","article-title":"Approximation capabilities of multilayer feedforward networks","volume":"4","author":"Hornik","year":"1991","journal-title":"Neural networks"},{"issue":"5","key":"10.3233\/JCS-210165_ref31","doi-asserted-by":"publisher","first-page":"359","DOI":"10.1016\/0893-6080(89)90020-8","article-title":"Multilayer feedforward networks are universal approximators","volume":"2","author":"Hornik","year":"1989","journal-title":"Neural networks"},{"issue":"3","key":"10.3233\/JCS-210165_ref32","first-page":"1","article-title":"Secure nonlocal denoising in outsourced images","volume":"12","author":"Hu","year":"2016","journal-title":"ACM Transactions on Multimedia Computing, Communications, and Applications (TOMM)"},{"key":"10.3233\/JCS-210165_ref33","unstructured":"Y.\u00a0Huang, L.\u00a0Malka, D.\u00a0Evans and J.\u00a0Katz, Efficient privacy-preserving biometric identification, in: Proc. of NDSS, 2011."},{"key":"10.3233\/JCS-210165_ref34","doi-asserted-by":"crossref","unstructured":"A.\u00a0Jacobi, M.\u00a0Chung, A.\u00a0Bernheim and C.\u00a0Eber, Portable chest X-ray in coronavirus disease-19 (COVID-19): A pictorial review, Clinical Imaging (2020).","DOI":"10.1016\/j.clinimag.2020.04.001"},{"issue":"6352","key":"10.3233\/JCS-210165_ref35","doi-asserted-by":"publisher","first-page":"692","DOI":"10.1126\/science.aam9710","article-title":"Deriving genomic diagnoses without revealing patient genomes","volume":"357","author":"Jagadeesh","year":"2017","journal-title":"Science"},{"key":"10.3233\/JCS-210165_ref36","doi-asserted-by":"publisher","DOI":"10.1109\/SP.2008.34"},{"key":"10.3233\/JCS-210165_ref37","unstructured":"C.\u00a0Juvekar, V.\u00a0Vaikuntanathan and A.\u00a0Chandrakasan, GAZELLE: A low latency framework for secure neural network inference, in: Proc. of 27th USENIX Security, 2018."},{"issue":"6","key":"10.3233\/JCS-210165_ref38","doi-asserted-by":"publisher","first-page":"473","DOI":"10.1038\/s42256-021-00337-8","article-title":"End-to-end privacy preserving deep learning on multi-institutional medical imaging","volume":"3","author":"Kaissis","year":"2021","journal-title":"Nature Machine Intelligence"},{"issue":"6","key":"10.3233\/JCS-210165_ref39","doi-asserted-by":"publisher","first-page":"305","DOI":"10.1038\/s42256-020-0186-1","article-title":"Secure, privacy-preserving and federated machine learning in medical imaging","volume":"2","author":"Kaissis","year":"2020","journal-title":"Nature Machine Intelligence"},{"key":"10.3233\/JCS-210165_ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3372297.3417872"},{"key":"10.3233\/JCS-210165_ref41","doi-asserted-by":"publisher","DOI":"10.1109\/SP40000.2020.00092"},{"issue":"6","key":"10.3233\/JCS-210165_ref42","doi-asserted-by":"publisher","first-page":"861","DOI":"10.1016\/S0893-6080(05)80131-5","article-title":"Multilayer feedforward networks with a nonpolynomial activation function can approximate any function","volume":"6","author":"Leshno","year":"1993","journal-title":"Neural networks"},{"key":"10.3233\/JCS-210165_ref43","doi-asserted-by":"crossref","unstructured":"S.\u00a0Li, K.\u00a0Xue, B.\u00a0Zhu, C.\u00a0Ding, X.\u00a0Gao, D.\u00a0Wei and T.\u00a0Wan, FALCON: A Fourier transform based approach for fast and secure convolutional neural network predictions, in: Proc. of IEEE\/CVF CVPR, 2020.","DOI":"10.1109\/CVPR42600.2020.00873"},{"key":"10.3233\/JCS-210165_ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-32692-0_16"},{"key":"10.3233\/JCS-210165_ref45","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2020.101765"},{"key":"10.3233\/JCS-210165_ref46","doi-asserted-by":"crossref","unstructured":"C.-W.\u00a0Lin and J.-S.\u00a0Wang, A digital circuit design of hyperbolic tangent sigmoid function for neural networks, in: 2008 IEEE International Symposium on Circuits and Systems, IEEE, 2008, pp.\u00a0856\u2013859.","DOI":"10.1109\/ISCAS.2008.4541553"},{"key":"10.3233\/JCS-210165_ref47","doi-asserted-by":"crossref","unstructured":"J.\u00a0Liu, M.\u00a0Juuti, Y.\u00a0Lu and N.\u00a0Asokan, Oblivious neural network predictions via minionn transformations, in: Proc. of ACM CCS, 2017.","DOI":"10.1145\/3133956.3134056"},{"key":"10.3233\/JCS-210165_ref48","doi-asserted-by":"publisher","first-page":"237","DOI":"10.1109\/TIFS.2021.3138611","article-title":"Leia: A lightweight cryptographic neural network inference system at the edge","volume":"17","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Information Forensics and Security"},{"key":"10.3233\/JCS-210165_ref49","doi-asserted-by":"crossref","unstructured":"X.\u00a0Liu and X.\u00a0Yi, Privacy-preserving collaborative medical time series analysis based on dynamic time warping, in: European Symposium on Research in Computer Security, Springer, 2019, pp.\u00a0439\u2013460.","DOI":"10.1007\/978-3-030-29962-0_21"},{"issue":"3","key":"10.3233\/JCS-210165_ref50","doi-asserted-by":"publisher","first-page":"1687","DOI":"10.1109\/TDSC.2020.3035592","article-title":"Privacy-preserving collaborative analytics on medical time series data","volume":"19","author":"Liu","year":"2022","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"10.3233\/JCS-210165_ref51","doi-asserted-by":"crossref","unstructured":"X.\u00a0Liu, Y.\u00a0Zheng, X.\u00a0Yuan and X.\u00a0Yi, MediSC: Towards secure and lightweight deep learning as a medical diagnostic service, in: European Symposium on Research in Computer Security, Springer, 2021, pp.\u00a0519\u2013541.","DOI":"10.1007\/978-3-030-88418-5_25"},{"key":"10.3233\/JCS-210165_ref52","unstructured":"Q.\u00a0Lou and L.\u00a0Jiang, SHE: A fast and accurate deep neural network for encrypted data, in: Proc. of NeurIPS, 2019, pp.\u00a010035\u201310043."},{"key":"10.3233\/JCS-210165_ref53","unstructured":"Q.\u00a0Lou, W.-J.\u00a0Lu, C.\u00a0Hong and L.\u00a0Jiang, Falcon: Fast spectral inference on encrypted data, Proc. of NeurIPS 33 (2020)."},{"key":"10.3233\/JCS-210165_ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.media.2021.102298"},{"key":"10.3233\/JCS-210165_ref56","doi-asserted-by":"crossref","unstructured":"P.\u00a0Mishra, R.\u00a0Lehmkuhl, A.\u00a0Srinivasan, W.\u00a0Zheng and R.A.\u00a0Popa, DELPHI: A cryptographic inference service for neural networks, in: USENIX Security Symposium, 2020.","DOI":"10.1145\/3411501.3419418"},{"key":"10.3233\/JCS-210165_ref57","unstructured":"P.\u00a0Mohassel and P.\u00a0Rindal, ABY3: A mixed protocol framework for machine learning, in: Proc. of ACM CCS, 2018."},{"key":"10.3233\/JCS-210165_ref58","doi-asserted-by":"crossref","unstructured":"P.\u00a0Mohassel and Y.\u00a0Zhang, SecureML: A system for scalable privacy-preserving machine learning, in: Proc. of IEEE S&P, 2017.","DOI":"10.1109\/SP.2017.12"},{"key":"10.3233\/JCS-210165_ref59","doi-asserted-by":"crossref","unstructured":"V.\u00a0Nikolaenko, U.\u00a0Weinsberg, S.\u00a0Ioannidis, M.\u00a0Joye, D.\u00a0Boneh and N.\u00a0Taft, Privacy-preserving ridge regression on hundreds of millions of records, in: Proc. of IEEE S&P, 2013.","DOI":"10.1109\/SP.2013.30"},{"key":"10.3233\/JCS-210165_ref61","unstructured":"A.\u00a0Patra, T.\u00a0Schneider, A.\u00a0Suresh and H.\u00a0Yalame, ABY2.0: Improved mixed-protocol secure two-party computation, in: 30th {USENIX} Security Symposium ({USENIX} Security 21), 2021."},{"key":"10.3233\/JCS-210165_ref63","doi-asserted-by":"crossref","unstructured":"D.\u00a0Rathee, M.\u00a0Rathee, R.K.K.\u00a0Goli, D.\u00a0Gupta, R.\u00a0Sharma, N.\u00a0Chandran and A.\u00a0Rastogi, SiRnn: A math library for secure RNN inference, in: IEEE Symposium on Security and Privacy, IEEE, 2021, pp.\u00a01003\u20131020.","DOI":"10.1109\/SP40001.2021.00086"},{"key":"10.3233\/JCS-210165_ref64","unstructured":"M.S.\u00a0Riazi, M.\u00a0Samragh, H.\u00a0Chen, K.\u00a0Laine, K.\u00a0Lauter and F.\u00a0Koushanfar, XONN: XNOR-based oblivious deep neural network inference, in: Proc. of 28th USENIX Security, 2019."},{"key":"10.3233\/JCS-210165_ref65","doi-asserted-by":"crossref","unstructured":"M.S.\u00a0Riazi, C.\u00a0Weinert, O.\u00a0Tkachenko, E.M.\u00a0Songhori, T.\u00a0Schneider and F.\u00a0Koushanfar, Chameleon: A hybrid secure computation framework for machine learning applications, in: Proc. of AsiaCCS, 2018.","DOI":"10.1145\/3196494.3196522"},{"key":"10.3233\/JCS-210165_ref66","doi-asserted-by":"crossref","unstructured":"B.D.\u00a0Rouhani, M.S.\u00a0Riazi and F.\u00a0Koushanfar, Deepsecure: Scalable provably-secure deep learning, in: Proceedings of the 55th Annual Design Automation Conference, 2018, pp.\u00a01\u20136.","DOI":"10.1145\/3195970.3196023"},{"key":"10.3233\/JCS-210165_ref68","doi-asserted-by":"crossref","unstructured":"A.-R.\u00a0Sadeghi and T.\u00a0Schneider, Generalized universal circuits for secure evaluation of private functions with application to data classification, in: International Conference on Information Security and Cryptology, Springer, 2008, pp.\u00a0336\u2013353.","DOI":"10.1007\/978-3-642-00730-9_21"},{"key":"10.3233\/JCS-210165_ref69","doi-asserted-by":"crossref","unstructured":"A.\u00a0Salem, P.\u00a0Berrang, M.\u00a0Humbert and M.\u00a0Backes, Privacy-preserving similar patient queries for combined biomedical data, Proc. of PETS (2019).","DOI":"10.2478\/popets-2019-0004"},{"key":"10.3233\/JCS-210165_ref70","unstructured":"A.\u00a0Sanyal, M.\u00a0Kusner, A.\u00a0Gascon and V.\u00a0Kanade, TAPAS: Tricks to accelerate (encrypted) prediction as a service, in: International Conference on Machine Learning, PMLR, 2018, pp.\u00a04490\u20134499."},{"key":"10.3233\/JCS-210165_ref71","doi-asserted-by":"crossref","unstructured":"M.J.\u00a0Sheller, G.A.\u00a0Reina, B.\u00a0Edwards, J.\u00a0Martin and S.\u00a0Bakas, Multi-institutional deep learning modeling without sharing patient data: A feasibility study on brain tumor segmentation, in: International MICCAI Brainlesion Workshop, Springer, 2018, pp.\u00a092\u2013104.","DOI":"10.1007\/978-3-030-11723-8_9"},{"key":"10.3233\/JCS-210165_ref72","doi-asserted-by":"crossref","unstructured":"O.\u00a0Tkachenko, C.\u00a0Weinert, T.\u00a0Schneider and K.\u00a0Hamacher, Large-scale privacy-preserving statistical computations for distributed genome-wide association studies, in: Proc. of ACM AsiaCCS, 2018.","DOI":"10.1145\/3196494.3196541"},{"issue":"6","key":"10.3233\/JCS-210165_ref73","doi-asserted-by":"publisher","first-page":"403","DOI":"10.1049\/ip-cdt:20030965","article-title":"Efficient digital implementation of the sigmoid function for reprogrammable logic","volume":"150","author":"Tommiska","year":"2003","journal-title":"IEE Proceedings-Computers and Digital Techniques"},{"key":"10.3233\/JCS-210165_ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CADSM.2019.8779253"},{"key":"10.3233\/JCS-210165_ref75","doi-asserted-by":"crossref","unstructured":"S.\u00a0Wagh, D.\u00a0Gupta and N.\u00a0Chandran, Securenn: 3-party secure computation for neural network training, Proc. of PETS (2019).","DOI":"10.2478\/popets-2019-0035"},{"key":"10.3233\/JCS-210165_ref78","doi-asserted-by":"crossref","unstructured":"X.S.\u00a0Wang, Y.\u00a0Huang, Y.\u00a0Zhao, H.\u00a0Tang, X.\u00a0Wang and D.\u00a0Bu, Efficient genome-wide, privacy-preserving similar patient query based on private edit distance, in: Proc. of ACM CCS, 2015.","DOI":"10.1145\/2810103.2813725"},{"key":"10.3233\/JCS-210165_ref79","doi-asserted-by":"crossref","unstructured":"A.\u00a0Wuraola and N.\u00a0Patel, SQNL: A new computationally efficient activation function, in: 2018 International Joint Conference on Neural Networks (IJCNN), IEEE, 2018, pp.\u00a01\u20137.","DOI":"10.1109\/IJCNN.2018.8489043"},{"key":"10.3233\/JCS-210165_ref80","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1016\/j.neucom.2021.02.030","article-title":"Efficient activation functions for embedded inference engines","volume":"442","author":"Wuraola","year":"2021","journal-title":"Neurocomputing"},{"key":"10.3233\/JCS-210165_ref81","doi-asserted-by":"crossref","unstructured":"P.\u00a0Xie, B.\u00a0Wu and G.\u00a0Sun, BAYHENN: Combining Bayesian deep learning and homomorphic encryption for secure DNN inference, in: Proc. of IJCAI, 2019, pp.\u00a04831\u20134837.","DOI":"10.24963\/ijcai.2019\/671"},{"key":"10.3233\/JCS-210165_ref82","doi-asserted-by":"crossref","unstructured":"L.\u00a0Yu, L.\u00a0Liu, C.\u00a0Pu, M.E.\u00a0Gursoy and S.\u00a0Truex, Differentially private model publishing for deep learning, in: Proc. of S&P, IEEE, 2019.","DOI":"10.1109\/SP.2019.00019"},{"key":"10.3233\/JCS-210165_ref83","doi-asserted-by":"crossref","unstructured":"Q.\u00a0Zhang, C.\u00a0Wang, H.\u00a0Wu, C.\u00a0Xin and T.V.\u00a0Phuong, GELU-net: A globally encrypted, locally unencrypted deep neural network for privacy-preserved learning, in: Proc. of IJCAI, 2018, pp.\u00a03933\u20133939.","DOI":"10.24963\/ijcai.2018\/547"},{"key":"10.3233\/JCS-210165_ref84","doi-asserted-by":"crossref","unstructured":"W.\u00a0Zheng, R.\u00a0Popa, J.E.\u00a0Gonzalez and I.\u00a0Stoica, Helen: Maliciously secure coopetitive learning for linear models, in: Proc. of IEEE S&P, 2019.","DOI":"10.1109\/SP.2019.00045"},{"issue":"6","key":"10.3233\/JCS-210165_ref85","doi-asserted-by":"publisher","first-page":"1285","DOI":"10.1109\/TIFS.2017.2656824","article-title":"Privacy-preserving image denoising from external cloud databases","volume":"12","author":"Zheng","year":"2017","journal-title":"IEEE Transactions on Information Forensics and Security"},{"issue":"3","key":"10.3233\/JCS-210165_ref86","doi-asserted-by":"publisher","first-page":"1261","DOI":"10.1109\/TDSC.2019.2907081","article-title":"Denoising in the dark: Privacy-preserving deep neural network-based image denoising","volume":"18","author":"Zheng","year":"2019","journal-title":"IEEE Transactions on Dependable and Secure Computing"},{"key":"10.3233\/JCS-210165_ref87","doi-asserted-by":"crossref","unstructured":"Y.\u00a0Zheng, H.\u00a0Duan and C.\u00a0Wang, Towards secure and efficient outsourcing of machine learning classification, in: Proc. of ESORICS, Springer, 2019.","DOI":"10.1007\/978-3-030-29959-0_2"},{"key":"10.3233\/JCS-210165_ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2018.8462073"},{"key":"10.3233\/JCS-210165_ref89","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-70604-3_5"}],"container-title":["Journal of Computer Security"],"original-title":[],"link":[{"URL":"https:\/\/content.iospress.com\/download?id=10.3233\/JCS-210165","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T20:45:40Z","timestamp":1777495540000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.medra.org\/servlet\/aliasResolver?alias=iospress&doi=10.3233\/JCS-210165"}},"subtitle":[],"editor":[{"given":"Elisa","family":"Bertino","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Haya","family":"Shulman","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]},{"given":"Michael","family":"Waidner","sequence":"additional","affiliation":[],"role":[{"role":"editor","vocabulary":"crossref"}]}],"short-title":[],"issued":{"date-parts":[[2022,11,23]]},"references-count":79,"journal-issue":{"issue":"6"},"URL":"https:\/\/doi.org\/10.3233\/jcs-210165","relation":{},"ISSN":["1875-8924","0926-227X"],"issn-type":[{"value":"1875-8924","type":"electronic"},{"value":"0926-227X","type":"print"}],"subject":[],"published":{"date-parts":[[2022,11,23]]}}}