Private predictive analysis on encrypted medical data
Open accessAbstract
Increasingly, confidential medical records are being stored in data centers hosted by hospitals or large companies. As sophisticated algorithms for predictive analysis on medical data continue to be developed, it is likely that, in the future, more and more computation will be done on private patient data. While encryption provides a tool for assuring the privacy of medical information, it limits the functionality for operating on such data. Conventional encryption methods used today provide only very restricted possibilities or none at all to operate on encrypted data without decrypting it first. Homomorphic encryption provides a tool for handling such computations on encrypted data, without decrypting the data, and without even needing the decryption key. In this paper, we discuss possible application scenarios for homomorphic encryption in order to ensure privacy of sensitive medical data. We describe how to privately conduct predictive analysis tasks on encrypted data using homomorphic encryption. As a proof of concept, we present a working implementation of a prediction service running in the cloud (hosted on Microsoft's Windows Azure), which takes as input private encrypted health data, and returns the probability for suffering cardiovascular disease in encrypted form. Since the cloud service uses homomorphic encryption, it makes this prediction while handling only encrypted data, learning nothing about the submitted confidential medical data.
Integrity signals
Registry
Cites
Statistics
Claims the paper makes
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
Transmission of gradients and partial parameters may lead to indirect privacy leakage.
“Nevertheless, the system is not sufficiently secure because the transmission of gradients and partial parameters may lead to indirect privacy leakage (Bos et al., 2014).”
From A review of applications in federated learning (2020) · cites this paper as Bos et al., 2014
Cites
An algorithm for the machine calculation of complex Fourier series
Cooley, J. W., & Tukey, J. W. (1965) · Mathematics of Computation · doi:10.1090/s0025-5718-1965-0178586-1 · Cited by 13,154 · see citing works
General Cardiovascular Risk Profile for Use in Primary Care: The Framingham Heart Study
D’Agostino, R. B., Vasan, R. S., Pencina, M. J., Wolf, P. A., Cobain, M., Massaro, J. M., & Kannel, W. B. (2008) · Circulation · doi:10.1161/circulationaha.107.699579 · Cited by 7,491 · see citing works
Fully homomorphic encryption using ideal lattices
Gentry, C. (2009) · Proceedings of the forty-first annual ACM symposium on Theory of computing · doi:10.1145/1536414.1536440 · Cited by 6,806 · see citing works
The Art of Computer Programming. Volume 2: Seminumerical Algorithms.
Taussky, O., & Knuth, D. E. (1970) · American Mathematical Monthly · doi:10.2307/2317055 · Cited by 3,863 · see citing works
Hilbe, J. M. (2009) · Chapman & Hall/CRC eBooks · doi:10.1201/9781420075779 · Cited by 2,616 · see citing works
The Art of Computer Programming
Worlton, W. J. (1968) · Nuclear Science and Engineering · doi:10.13182/nse68-a19548 · Cited by 2,251 · see citing works
Evaluating trauma care: the TRISS method. Trauma Score and the Injury Severity Score.
Boyd, C. R., Tolson, M. A., & Copes, W. S. (1987) · PubMed · Cited by 1,954 · see citing works
BOYD, C. R., Tolson, M. A., & Copes, W. S. (1987) · The Journal of Trauma: Injury, Infection, and Critical Care · doi:10.1097/00005373-198704000-00005 · Cited by 1,843 · see citing works
2014 IEEE Symposium on Security and Privacy
(2014) · doi:10.1109/sp16517.2014 · Cited by 1,388 · see citing works
Fully Homomorphic Encryption without Modulus Switching from Classical GapSVP
Brakerski, Z. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32009-5_50 · Cited by 1,282 · see citing works
Identifying Personal Genomes by Surname Inference
Gymrek, M., McGuire, A. L., Golan, D., Halperin, E., & Erlich, Y. (2013) · Science · doi:10.1126/science.1229566 · Cited by 1,228 · see citing works
LaValley, M. P. (2008) · Circulation · doi:10.1161/circulationaha.106.682658 · Cited by 1,163 · see citing works
Non-interactive Verifiable Computing: Outsourcing Computation to Untrusted Workers
Gennaro, R., Gentry, C., & Parno, B. J. (2010) · Lecture notes in computer science · doi:10.1007/978-3-642-14623-7_25 · Cited by 1,156 · see citing works
Fully Homomorphic Encryption from Ring-LWE and Security for Key Dependent Messages
Brakerski, Z., & Vaikuntanathan, V. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-22792-9_29 · Cited by 1,114 · see citing works
Schnelle Multiplikation großer Zahlen
Schönhage, A., & Strassen, V. (1971) · Computing · doi:10.1007/bf02242355 · Cited by 1,107 · see citing works
Can homomorphic encryption be practical?
Naehrig, M., Lauter, K., & Vaikuntanathan, V. (2011) · Cloud Computing Security Workshop · doi:10.1145/2046660.2046682 · Cited by 1,027 · see citing works
On-the-fly multiparty computation on the cloud via multikey fully homomorphic encryption
López-Alt, A., Tromer, E., & Vaikuntanathan, V. (2012) · ACM Symposium on Theory of Computing (STOC) · doi:10.1145/2213977.2214086 · Cited by 916 · see citing works
Pinocchio: Nearly Practical Verifiable Computation
Parno, B., Howell, J., Gentry, C., & Raykova, M. (2013) · 2013 IEEE Symposium on Security and Privacy · doi:10.1109/sp.2013.47 · Cited by 864 · see citing works
A firm foundation for private data analysis
Dwork, C. (2010) · Communications of the ACM · doi:10.1145/1866739.1866758 · Cited by 858 · see citing works
Homomorphic Evaluation of the AES Circuit
Gentry, C., Halevi, S., & Smart, N. P. (2012) · Lecture notes in computer science · doi:10.1007/978-3-642-32009-5_49 · Cited by 800 · see citing works
Fast fourier transform and convolution algorithms
(1981) · Mathematics and Computers in Simulation · doi:10.1016/0378-4754(81)90075-6 · Cited by 679 · see citing works
Fully homomorphic SIMD operations
Smart, N. P., & Vercauteren, F. (2012) · Designs Codes and Cryptography · doi:10.1007/s10623-012-9720-4 · Cited by 663 · see citing works
BKZ 2.0: Better Lattice Security Estimates
Chen, Y., & Nguyễn, P. Q. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-25385-0_1 · Cited by 601 · see citing works
Making NTRU as Secure as Worst-Case Problems over Ideal Lattices
Stehlé, D., & Steinfeld, R. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-20465-4_4 · Cited by 444 · see citing works
Improved Security for a Ring-Based Fully Homomorphic Encryption Scheme
Bos, J. W., Lauter, K., Loftus, J., & Naehrig, M. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-45239-0_4 · Cited by 428 · see citing works
ML Confidential: Machine Learning on Encrypted Data
Graepel, T., Lauter, K., & Naehrig, M. (2013) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-37682-5_1 · Cited by 423 · see citing works
Benaloh, J., Chase, M., Horvitz, E., & Lauter, K. (2009) · doi:10.1145/1655008.1655024 · Cited by 358 · see citing works
Cardiovascular Disease Risk Assessment: Insights from Framingham
D’Agostino, R. B., Pencina, M. J., Massaro, J. M., & Coady, S. (2013) · Global Heart · doi:10.1016/j.gheart.2013.01.001 · Cited by 331 · see citing works
Fully Homomorphic Encryption without Bootstrapping.
Brakerski, Z., Gentry, C., & Vaikuntanathan, V. (2011) · Cited by 324 · see citing works
Boekholdt, S. M., Sacks, F. M., Jukema, J. W., Shepherd, J., Freeman, D. J., McMahon, A. D., Cambien, F., Nicaud, V., de Grooth, G. J., Talmud, P. J., et al. (2005) · Circulation · doi:10.1161/01.cir.0000153341.46271.40 · Cited by 308 · see citing works
Festa, A., Williams, K., Hanley, A. J., Otvos, J. D., Goff, D. C., Wagenknecht, L. E., & Haffner, S. M. (2005) · Circulation · doi:10.1161/circulationaha.104.512079 · Cited by 259 · see citing works
Privacy preserving EHR system using attribute-based infrastructure
Narayan, S., Gagné, M., & Safavi-Naini, R. (2010) · Proceedings of the 2010 ACM workshop on Cloud computing security workshop · doi:10.1145/1866835.1866845 · Cited by 257 · see citing works
Blankstein, R., Ward, R. P., Arnsdorf, M. F., Jones, B., Lou, Y., & Pine, M. B. (2005) · Circulation · doi:10.1161/circulationaha.104.525139 · Cited by 253 · see citing works
A Comparison of the Homomorphic Encryption Schemes FV and YASHE
Lepoint, T., & Naehrig, M. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-06734-6_20 · Cited by 178 · see citing works
On syntactic anonymity and differential privacy
Clifton, C., & Tassa, T. (2013) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew.2013.6547433 · Cited by 154 · see citing works
A Multivariate Logistic Regression Equation to Screen for Diabetes
Tabaei, B. P., & Herman, W. H. (2002) · Diabetes Care · doi:10.2337/diacare.25.11.1999 · Cited by 146 · see citing works
Can homomorphic encryption be practical
Lauter, K., Naehrig, M., & Vaikuntanathan, V. (2011) · Cited by 132 · see citing works
Advances in Cryptology – CRYPTO 2013
Canetti, R., & Garay, J. A. (2013) · Lecture notes in computer science · doi:10.1007/978-3-642-40084-1 · Cited by 110 · see citing works
Cramer, R. L. (2005) · Data Archiving and Networked Services (DANS) · Cited by 108 · see citing works
Fast polynomial transform algorithms for digital convolution
Nussbaumer, H. (1980) · IEEE Transactions on Acoustics Speech and Signal Processing · doi:10.1109/tassp.1980.1163372 · Cited by 104 · see citing works
Framingham Stroke Risk Profile and poor cognitive function: a population-based study
Llewellyn, D. J., Lang, I., Xie, J., Huppert, F. A., Melzer, D. R., & Langa, K. M. (2008) · BMC Neurology · doi:10.1186/1471-2377-8-12 · Cited by 90 · see citing works
Large Medical Databases, Population-Based Research, and Patient Confidentiality
Simon, G. E., Unützer, J., Young, B. E., & Pincus, H. A. (2000) · American Journal of Psychiatry · doi:10.1176/appi.ajp.157.11.1731 · Cited by 51 · see citing works
Information Security and Cryptology - ICISC 2010
Rhee, K.-H., & Nyang, D. (2011) · Lecture notes in computer science · doi:10.1007/978-3-642-24209-0 · Cited by 51 · see citing works
Flagged first, then by citations
1 of the 44 references couldn’t be matched to a known paper.
Cited by
Sorted by citations
Membership Inference Attacks Against Machine Learning Models
Shokri, R., Stronati, M., Song, C., & Shmatikov, V. (2017) · 2017 IEEE Symposium on Security and Privacy (SP) · doi:10.1109/sp.2017.41 · Cited by 4,754 · see citing works
“This also holds for the models trained by computing on encrypted data [4], [6], [35].”
MethodHomomorphic Encryption for Arithmetic of Approximate Numbers
Cheon, J. H., Kim, A., Kim, M., & Song, Y. (2017) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-70694-8_15 · Cited by 2,522 · see citing works
“8 s of evaluation time of [3,9] without parallelization, respectively.”
BackgroundMethodInfluentialPrivacy-preserving deep learning
Shokri, R., & Shmatikov, V. (2015) · Proceedings of the 22nd ACM SIGSAC Conference on Computer and Communications Security · doi:10.1145/2810103.2813687 · Cited by 2,356 · see citing works
“Techniques that protect privacy of the model include privacypreserving probabilistic inference [38], privacy-preserving speaker identification [36], and computing on encrypted data [3, 6, 55].”
BackgroundA review of applications in federated learning
Li, L., Fan, Y., Tse, M., & Lin, K.-Y. (2020) · Computers & Industrial Engineering · doi:10.1016/j.cie.2020.106854 · Cited by 1,559 · see citing works
“Nevertheless, the system is not sufficiently secure because the transmission of gradients and partial parameters may lead to indirect privacy leakage (Bos et al., 2014).”
BackgroundMachine Learning Classification over Encrypted Data
Bost, R., Popa, R. A., Tu, S., & Goldwasser, S. (2015) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2015.23241 · Cited by 683 · see citing works
“The few works on privacy-preserving classification either consider a weaker security setting in which the client learns the model [16] or focus on specific classifiers (e.”
BackgroundThapa, C., & Camtepe, S. A. (2020) · Computers in Biology and Medicine · doi:10.1016/j.compbiomed.2020.104130 · Cited by 424 · see citing works
“In another work, (leveled) homomorphic encryption was implemented to conduct predictive analyses (e.g., logistic regression) on medical data [121] privately in a cloud service.”
MethodA Systematic Review of Homomorphic Encryption and Its Contributions in Healthcare Industry
Munjal, K., & Bhatia, R. (2023) · Complex & Intelligent Systems · doi:10.1007/s40747-022-00756-z · Cited by 269 · see citing works
“In [74], author presented an approach that predicts heart attack probability based upon few body measurements.”
BackgroundSecure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation
Kim, M., Song, Y., Wang, S., Xia, Y., & Jiang, X. (2018) · JMIR Medical Informatics · doi:10.2196/medinform.8805 · Cited by 257 · see citing works
“TechniquesProblemReference Homomorphic encryptionLinear means classifier/discriminative analysisGraepel et al [11] Homomorphic encryptionPrediction using learned logistic regression modelBos et al [14] Homomorphic encryptionPrediction using learned neural networksDowlin et al [15] Additive homomorphic encryptionLogist…”
MethodInfluentialA machine learning model for improving healthcare services on cloud computing environment
Abdelaziz, A., Elhoseny, M., Salama, A. S., & Riad, A. M. (2018) · Measurement · doi:10.1016/j.measurement.2018.01.022 · Cited by 234 · see citing works
FPGA-Based High-Performance Parallel Architecture for Homomorphic Computing on Encrypted Data
Roy, S. S., Turan, F., Jarvinen, K. U., Vercauteren, F., & Verbauwhede, I. M. R. (2019) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca.2019.00052 · Cited by 195 · see citing works
“…many interesting HE applications are: privacy-preserving services for information storage and processing in business and health-care applications [2], encrypted web-search engine [3], electronic voting, and privacy-preserving prediction from consumption data in smart electricity meters [4],…”
BackgroundScalable and Secure Logistic Regression via Homomorphic Encryption
Aono, Y., Hayashi, T., Phong, L. T., & Wang, L. (2016) · ACM Conference on Data and Application Security and Privacy (CODASPY) · doi:10.1145/2857705.2857731 · Cited by 183 · see citing works
“This work complements [4] by protecting the training data in producing the regression coefficients.”
BackgroundMethodPrivately Evaluating Decision Trees and Random Forests
Wu, D. J., Feng, T., Naehrig, M., & Lauter, K. (2016) · Proceedings on Privacy Enhancing Technologies · doi:10.1515/popets-2016-0043 · Cited by 182 · see citing works
“While these methods have been successfully applied to several problems in privacypreserving data mining [16, 39], the methods are limited to simple functionalities.”
MethodPrivate Computation on Encrypted Genomic Data
Lauter, K., López-Alt, A., & Naehrig, M. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16295-9_1 · Cited by 159 · see citing works
cuHE: A Homomorphic Encryption Accelerator Library
Dai, W., & Sunar, B. (2016) · Lecture notes in computer science · doi:10.1007/978-3-319-29172-7_11 · Cited by 149 · see citing works
“in [1] showed how to privately perform predictive analysis tasks on encrypted medical data.”
BackgroundCheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference
Reagen, B., Choi, W.-S., Ko, Y., Lee, V. T., Lee, H.-H. S., Wei, G.-Y., & Brooks, D. M. (2021) · IEEE International Symposium on High-Performance Computer Architecture (HPCA) · doi:10.1109/hpca51647.2021.00013 · Cited by 154 · see citing works
“Such solutions include (i) differential privacy (DP) [4], [13], [18], [21], (ii) secure multi-party compute (MPC) [33], [37], [50], [51], and (iii) homomorphic encryption (HE) [7], [29], [32], [55].”
Efficient and Privacy-Preserving Online Medical Prediagnosis Framework Using Nonlinear SVM
Zhu, H., Liu, X., Lu, R., & Li, H. (2016) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2548248 · Cited by 142 · see citing works
“To address these challenges, different homomorphic encryption techniques, which include partially homomorphic cryptosystems, fully homomorphic cryptosystems, and somewhat homomorphic cryptosystems [20], are introduced in the medical diagnosis system [21]–[23].”
BackgroundZhang, C., Zhu, L., Xu, C. L., & Lu, R. (2017) · Future Generation Computer Systems · doi:10.1016/j.future.2017.09.002 · Cited by 141 · see citing works
Crypto-Nets: Neural Networks over Encrypted DataPreprint
Xie, P., Bilenko, M., Finley, T., Gilad-Bachrach, R., Lauter, K., & Naehrig, M. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1412.6181 · Cited by 138 · see citing works
“…studied how to do HE-based privacy-preserving training or prediction of linear regression (Nikolaenko et al., 2013b; Wu & Haven, 2012), linear classifiers (Bos et al., 2014; Bost et al., 2014; Graepel et al., 2013), decision trees (Bost et al., 2014), matrix factorization (Nikolaenko et al., 2013a).”
BackgroundMethodPrivate genome analysis through homomorphic encryption
Kim, M., & Lauter, K. (2015) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-15-s5-s3 · Cited by 136 · see citing works
“[15] applied HE to machine learning, and described how to privately conduct predictive analysis based on an encrypted learned model.”
MethodPEGASUS: Bridging Polynomial and Non-polynomial Evaluations in Homomorphic Encryption
Lu, W.-J., Huang, Z., Hong, C., Ma, Y., & Qu, H. (2021) · IEEE Symposium on Security and Privacy (S&P) · doi:10.1109/sp40001.2021.00043 · Cited by 134 · see citing works
“A potential application of HE is secure outsourcing [3], [36], where all the data comes from clients.”
BackgroundRevisiting Lattice Attacks on Overstretched NTRU Parameters
Kirchner, P., & Fouque, P.-A. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-56620-7_1 · Cited by 133 · see citing works
“The parameters proposed for schemes using similar overstretched NTRU assumption, such as in homomorphic encryption [7,30,15,16], [14,10,31,18] or in private information retrieval [17], are also broken in practical time using LLL.”
ResultPrivacy-preserving neural networks with Homomorphic encryption: Challenges and opportunities
Pulido-Gaytan, B., Tchernykh, A., Cortés-Mendoza, J. M., Babenko, M., Radchenko, G., Avetisyan, A., & Drozdov, A. Y. (2021) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-021-01076-8 · Cited by 126 · see citing works
Manual for Using Homomorphic Encryption for Bioinformatics
Dowlin, N., Gilad-Bachrach, R., Laine, K., Lauter, K., Naehrig, M., & Wernsing, J. R. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2016.2622218 · Cited by 124 · see citing works
“In [31], logistic regression and the Cox proportional hazard model were implemented as representative examples for disease prediction.”
BackgroundMethodA systematic review on the status and progress of homomorphic encryption technologies
Alloghani, M. A., Alani, M. M., Al‐Jumeily, D., Baker, T., Mustafina, J., Hussain, A. J., & Aljaaf, A. J. (2019) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2019.102362 · Cited by 119 · see citing works
Wang, S., Zhang, Y., Dai, W., Lauter, K., Kim, M., Tang, Y., Xiong, H., & Jiang, X. (2015) · Bioinformatics · doi:10.1093/bioinformatics/btv563 · Cited by 108 · see citing works
Privacy-Preserving Decision Trees Evaluation via Linear Functions
Tai, R. K. H., Ma, J. P. K., Zhao, Y., & Chow, S. S. M. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-66399-9_27 · Cited by 109 · see citing works
Metaverse Wearables for Immersive Digital Healthcare: A Review
Kim, K., Yang, H., Lee, J.-H., & Lee, W. G. (2023) · Advanced Science · doi:10.1002/advs.202303234 · Cited by 105 · see citing works
Revisiting Cryptographic Accumulators, Additional Properties and Relations to Other Primitives
Derler, D., Hanser, C., & Slamanig, D. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-16715-2_7 · Cited by 100 · see citing works
A Survey on federated learning
Li, L., Fan, Y., & Lin, K. (2020) · International Conference on Control and Automation · doi:10.1109/icca51439.2020.9264412 · Cited by 91 · see citing works
“Nevertheless, the system is not sufficiently secure because the transmission of gradients and partial parameters may lead to indirect privacy leakage [37].”
BackgroundMSCryptoNet: Multi-Scheme Privacy-Preserving Deep Learning in Cloud Computing
Kwabena, O.-A., Qin, Z., Zhuang, T., & Qin, Z. (2019) · IEEE Access · doi:10.1109/access.2019.2901219 · Cited by 92 · see citing works
“…existing works considering the problems confronting the security of the cloud architecture [36], [37], cloud storage [38]–[40], data mining [30], [41], authentication of protocols [53], security robustness [54], flexible access control of sharing files [55]and privacy-preserving model [7],…”
BackgroundPrivacy-preserving edge federated learning for intelligent mobile-health systems
Aminifar, A., Shokri, M., & Aminifar, A. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.07.035 · Cited by 99 · see citing works
“Several state-of-the-art studies propose solutions for learning from decentralized data that are based on homomorphic cryptography or SMC [88, 89, 90, 91].”
BackgroundTrusted AI in Multiagent Systems: An Overview of Privacy and Security for Distributed Learning
Ma, C., Li, J., Wei, K., Liu, B., Ding, M., Yuan, L., Han, Z., & Vincent Poor, H. (2023) · Proceedings of the IEEE · doi:10.1109/jproc.2023.3306773 · Cited by 96 · see citing works
“Typical examples are, neural networks [78]–[80], matrix factorization [81], linear regressions [82], decision trees [83], and linear classifiers [84], [85].”
BackgroundEfficient Private Statistics with Succinct Sketches
Melis, L., Danezis, G., & Cristofaro, E. D. (2016) · Network and Distributed System Security Symposium · doi:10.14722/ndss.2016.23175 · Cited by 94 · see citing works
Privacy-preserving logistic regression training
Bonte, C., & Vercauteren, F. (2018) · BMC Medical Genomics · doi:10.1186/s12920-018-0398-y · Cited by 85 · see citing works
(2017) · doi:10.1587/transinf.2015inp0020 · Cited by 89 · see citing works
“The papers [9], [22] do not consider the training phase of logistic regression.”
BackgroundMethodInfluentialA survey on federated learning in data mining
Yu, B., Mao, W., Lv, Y., Zhang, C. B. C., & Xie, Y. (2021) · Wiley Interdisciplinary Reviews Data Mining and Knowledge Discovery · doi:10.1002/widm.1443 · Cited by 78 · see citing works
“Although the private data on clients never comes out of local storage during training process, the federated system is not safe enough, because the transmission of parameters may lead to indirect privacy leakage (Bhowmick et al., 2018; Bos et al., 2014; Kairouz et al., 2019).”
BackgroundPrivacy-preserving techniques of genomic data—a survey
Aziz, M. M. A., Sadat, M. N., Alhadidi, D., Wang, S., Jiang, X., Brown, C. L., & Mohammed, N. (2017) · Briefings in Bioinformatics · doi:10.1093/bib/bbx139 · Cited by 72 · see citing works
Liu, J., Huang, G., Hyyppa, J. M., Li, J., Gong, X., & Jiang, X. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.120492 · Cited by 79 · see citing works
Lu, W.-J., Yamada, Y., & Sakuma, J. (2015) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-15-s5-s1 · Cited by 70 · see citing works
“[4] proposed a working implementation of cloud service for private computation of encrypted health * Correspondence: riku@mdl.”
BackgroundOutsourced privacy-preserving classification service over encrypted data
Li, T., Huang, Z., Li, P., Liu, Z., & Jia, C. (2018) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2017.12.021 · Cited by 70 · see citing works
Accelerating Homomorphic Evaluation on Reconfigurable Hardware
Pöppelmann, T., Naehrig, M., Putnam, A. R., & Macías, A. (2015) · Lecture notes in computer science · doi:10.1007/978-3-662-48324-4_8 · Cited by 69 · see citing works
Combining Molecular, Imaging, and Clinical Data Analysis for Predicting Cancer Prognosis
Lobato-Delgado, B., Priego, B., & Morillo, D. (2022) · Cancers · doi:10.3390/cancers14133215 · Cited by 68 · see citing works
Adversarial machine learning: a review of methods, tools, and critical industry sectors
Pelekis, S., Koutroubas, T., Blika, A., Berdelis, A., Karakolis, E., Ntanos, C., Spiliotis, E., & Askounis, D. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11147-4 · Cited by 75 · see citing works
Kim, J., Koo, D., Kim, Y., Yoon, H., Shin, J., & Kim, S. (2018) · ACM Transactions on Privacy and Security · doi:10.1145/3212509 · Cited by 74 · see citing works
“Many works have been proposed to solve the privacy issues for various machine-learning algorithms, and some of their basic operations can be protected using cryptography such as classification [5] and regression [4, 44].”
BackgroundProvably Weak Instances of Ring-LWE
Elias, Y., Lauter, K., Özman, E., & Stange, K. E. (2015) · Lecture notes in computer science · doi:10.1007/978-3-662-47989-6_4 · Cited by 64 · see citing works
Hou, D., Zhang, J., Man, K. L., Ma, J., & Peng, Z. (2021) · Information Communication Technologies Conference (ICTC) · doi:10.1109/ictc51749.2021.9441499 · Cited by 62 · see citing works
“…public PoF VFChain [19] Single point failure, poison attack Public Algorand BLADE-FL [20] Single point failure Public PoW BFLC [21] Single point failure, poison attack, lack of motivation Public Committee VBFL [22] Single point failure, poison attack, lack of motivation Public PoS [28] [29].”
BackgroundFORESEE: Fully Outsourced secuRe gEnome Study basEd on homomorphic Encryption
Zhang, Y., Dai, W., Jiang, X., Xiong, H., & Wang, S. (2015) · BMC Medical Informatics and Decision Making · doi:10.1186/1472-6947-15-s5-s5 · Cited by 61 · see citing works
“Considering that secure division operation is not available in existing HME-based schemes [15,17,22], we construct a one-to-one mapping function from floating numbers to a set of encrypted positive integers.”
BackgroundMethodResultInfluentialPrivacy Policy and Technology in Biomedical Data Science
Arellano, A. M., Dai, W., Wang, S., Jiang, X., & Lucila Ohno-machado, A. (2018) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-080917-013416 · Cited by 61 · see citing works
“Advanced security models can enable confidentiality during the entire data lifecycle, including computation on encrypted data (12).”
BackgroundArtificial Intelligence for Social Good: A SurveyPreprint
Shi, Z. R., Wang, C., & Fang, F. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2001.01818 · Cited by 108 · see citing works
“predict the probability for su ering cardiovascular disease [411].”
BackgroundPrivacy-preserving self-serviced medical diagnosis scheme based on secure multi-party computation
Li, D., Liao, X., Xiang, T., Wu, J., & Le, J. (2019) · Computers & Security · doi:10.1016/j.cose.2019.101701 · Cited by 60 · see citing works
Protecting genomic data analytics in the cloud: state of the art and opportunities
Tang, H., Jiang, X., Wang, X., Wang, S., Sofia, H. J., Fox, D., Lauter, K., Malin, B., Telenti, A., Xiong, L., et al. (2016) · BMC Medical Genomics · doi:10.1186/s12920-016-0224-3 · Cited by 60 · see citing works
“A notable example is a computation partition [29], which offloads some computation to the local system of the data owner to simplify the work that needs to be performed in the public cloud.”
BackgroundUnsupervised Machine Learning on Encrypted Data
Jäschke, A., & Armknecht, F. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-10970-7_21 · Cited by 60 · see citing works
Differential Privacy for Data and Model Publishing of Medical Data
Sun, Z., Wang, Y., Shu, M., Liu, R., & Zhao, H. (2019) · IEEE Access · doi:10.1109/access.2019.2947295 · Cited by 56 · see citing works
“Because medical data contain a large amount of sensitive information, it may reveal the privacy of patients both when publishing data and training data in machine learning [3], [4].”
BackgroundAn Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies
Enthoven, D., & Al-Ars, Z. (2021) · Studies in computational intelligence · doi:10.1007/978-3-030-70604-3_8 · Cited by 61 · see citing works
Gong, Y., Chang, X., Mišić, J., Mišić, V. B., Wang, J., & Zhu, H. (2024) · Cybersecurity · doi:10.1186/s42400-023-00187-4 · Cited by 60 · see citing works
SPABox: Safeguarding Privacy During Deep Packet Inspection at a MiddleBox
Fan, J., Guan, C., Ren, K., Cui, Y., & Qiao, C. (2017) · IEEE/ACM Transactions on Networking · doi:10.1109/tnet.2017.2753044 · Cited by 54 · see citing works
“[17] work showed how the computation of medical prediction functions over the”
Practical Privacy-Preserving Data Science With Homomorphic Encryption: An Overview
Iezzi, M. (2020) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata50022.2020.9377989 · Cited by 53 · see citing works
“For the PPaaS scenario, predictions are mainly obtained via: (i) a logistic regression, as in [46], [3], [60]; (ii) Neural Networks (NN), as in [45], [48], [53], [58].”
BackgroundMethodInfluentialSecureMed: Secure Medical Computation Using GPU-Accelerated Homomorphic Encryption Scheme
Khedr, A. F., & Gulak, P. G. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2657458 · Cited by 51 · see citing works
“Our GPU implementation gives us a further 104× (and 410×) speedup with overall speedup of 6085× (and 24011×) over [18] using a single GPU (and four GPUs), respectively.”
BackgroundMethodInfluentialA Survey on Privacy-Preserving Machine Learning with Fully Homomorphic Encryption
Pulido-Gaytan, L. B., Tchernykh, A. N., Cortés-Mendoza, J. M., Babenko, M. G., & Radchenko, G. (2021) · Communications in computer and information science · doi:10.1007/978-3-030-68035-0_9 · Cited by 52 · see citing works
Privacy-preserving human activity sensing: A survey
Yang, Y., Hu, P., Shen, J., Cheng, H., An, Z., & Liu, X. (2024) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100204 · Cited by 51 · see citing works
“The and data obfuscation methods mentioned in Section 3.1 information for individual activity sensing can [94, 95, 96].”
MethodInfluentialTowards Privacy-Preserving Medical Cloud Computing Using Homomorphic Encryption
Kocabaş, Ö., & Soyata, T. (2019) · IGI Global eBooks · doi:10.4018/978-1-5225-9863-3.ch005 · Cited by 49 · see citing works
An Overview of Privacy in Machine LearningPreprint
Cristofaro, E. D. (2020) · arXiv (Cornell University) · doi:10.48550/arxiv.2005.08679 · Cited by 91 · see citing works
“…secure multi-party computation (SMC) and fully homomorphic encryption (FHE) have been proposed to securely train supervised machine learning models, such as matrix factor-8 ization [38], linear classifiers [6, 22], decision trees [7, 31], linear regressors [12], and neural networks [5, 11, 32, 36].”
Encrypted statistical machine learning: new privacy preserving methodsPreprint
Aslett, L. J. M., Esperança, P. M., & Holmes, C. C. (2015) · arXiv (Cornell University) · doi:10.48550/arxiv.1508.06845 · Cited by 48 · see citing works
“…such as small-P linear regression ( P ≤ 5; Wu and Haven, 2012) and predictive machine learning using pre-trained models (e.g., logistic regression; Bos et al. , 2014) In Section 2 a brief recap of homomorphic encryption and consequences for data representation is presented, with the unfamiliar…”
MethodCREDO: Efficient and privacy-preserving multi-level medical pre-diagnosis based on ML-kNN
Zhu, D., Zhu, H., Liu, X., Li, H., Wang, F., Li, H., & Feng, D. (2019) · Information Sciences · doi:10.1016/j.ins.2019.11.041 · Cited by 47 · see citing works
Archer, D. W., Trilla, J. M. C., Dagit, J., Malozemoff, A. J., Polyakov, Y., Rohloff, K. R., & Ryan, G. W. (2019) · doi:10.1145/3338469.3358945 · Cited by 46 · see citing works
“Over the past several years, HE has become increasingly performant and practical for real-world applications [11, 20, 23, 33].”
BackgroundPrivacy-preserving genotype imputation with fully homomorphic encryption
Gürsoy, G., Chielle, E., Brannon, C. M., Maniatakos, M., & Gerstein, M. (2021) · Cell Systems · doi:10.1016/j.cels.2021.10.003 · Cited by 45 · see citing works
Private queries on encrypted genomic data
Çetin, G. S., Chen, H., Laine, K., Lauter, K., Rindal, P., & Xia, Y. (2017) · BMC Medical Genomics · doi:10.1186/s12920-017-0276-z · Cited by 45 · see citing works
“…tasks that have been demonstrated to be viable on homomorphically encrypted data include heart attack risk prediction from encrypted health data [6], and genomic computations such as Pearson Goodness-of-Fit test, Cochran-Armitage Test for Trend, measures of linkage disequilibrium, and…”
MethodExploring Collection of Sign Language Datasets: Privacy, Participation, and Model Performance
Bragg, D., Koller, O., Caselli, N. K., & Thies, W. (2020) · International ACM SIGACCESS Conference on Computers and Accessibility (ASSETS) · doi:10.1145/3373625.3417024 · Cited by 48 · see citing works
“A variety of machine learning models can be built on encrypted data: simple predictive analysis [10], decision trees, hyperplane decision, and Naive Bayes [11] low-degree polynomial classifcation [49], and neural networks [48].”
BackgroundDepth Optimized Efficient Homomorphic Sorting
Çetin, G. S., Doröz, Y., Sunar, B., & Savaş, E. (2015) · Lecture notes in computer science · doi:10.1007/978-3-319-22174-8_4 · Cited by 44 · see citing works
HE-Friendly Algorithm for Privacy-Preserving SVM Training
Park, S., Byun, J., Lee, J., Cheon, J. H., & Lee, J. (2020) · IEEE Access · doi:10.1109/access.2020.2981818 · Cited by 44 · see citing works
“Several works have been conducted on secure computations in machine learning algorithms with fully homomorphic encryptions: prediction phases [2]–[4] and training phases [5], [6] of the Logistic Regression Model (LRM), decision trees inference phases [7], and deep neural network inference phases…”
BackgroundSarkar, E., Chielle, E., Gürsoy, G., Mazonka, O., Gerstein, M., & Maniatakos, M. (2021) · IEEE Access · doi:10.1109/access.2021.3093005 · Cited by 44 · see citing works
“FHE has been used for medical data analysis such as on studies related to the analysis of Electro Cardiogram (ECG) [15] and on diabetes and heart disease studies [16].”
MethodWani, R. U. Z., Thabit, F., & Can, Ö. (2024) · Security and Privacy · doi:10.1002/spy2.409 · Cited by 50 · see citing works
“88,89 Homomorphic encryption of data prevents attackers from accessing confidential medical data.”
PRESAGE: PRivacy-preserving gEnetic testing via SoftwAre Guard Extension
Chen, F., Wang, C., Dai, W., Jiang, X., Mohammed, N., Aziz, M. M. A., Sadat, M. N., Şahinalp, S. C., Lauter, K., & Wang, S. (2017) · BMC Medical Genomics · doi:10.1186/s12920-017-0281-2 · Cited by 44 · see citing works
“Many HME-based applications have been studied for safeguarding linear classification [23], predictive analysis on encrypted medical data [24], genetic association studies [25, 26], Edit distance computation [27], GWAS study using exact logistic regression [28].”
MethodSoni, H., Grando, A., Murcko, A. C., Diaz, S., Mukundan, M., Idouraine, N., Karway, G. K., Todd, M. W., Chern, D., Dye, C., et al. (2019) · Journal of Biomedical Informatics · doi:10.1016/j.jbi.2019.103338 · Cited by 43 · see citing works
Private Data Analytics on Biomedical Sensing Data via Distributed Computation
Gong, Y., Fang, Y. M., & Guo, Y. (2016) · IEEE Transactions on Computational Biology and Bioinformatics · doi:10.1109/tcbb.2016.2515610 · Cited by 42 · see citing works
“There are a number of papers on private computation on medical data, but most of them focus on simple computations such as searching on encrypted medical data [37], computing statistical functions such as sum and variance [38], or performing predictive analysis tasks on encrypted data [26].”
BackgroundMethodEisenträger, K., Hallgren, S., & Lauter, K. (2014) · Lecture notes in computer science · doi:10.1007/978-3-319-13051-4_11 · Cited by 42 · see citing works
High-Precision Arithmetic in Homomorphic Encryption
Chen, H., Laine, K., Player, R., & Xia, Y. (2018) · Lecture notes in computer science · doi:10.1007/978-3-319-76953-0_7 · Cited by 41 · see citing works
“Several encoding methods for integers and rational numbers have been proposed in the literature [38, 10, 32, 21, 20, 16], but all of these have a common limitation: the decoding operation will work correctly only as long as the homomorphic operations do not cause the underlying plaintext polynomial coefficients to be…”
BackgroundBlindfolded Evaluation of Random Forests with Multi-Key Homomorphic Encryption
Aloufi, A., Hu, P., Wong, H. W. H., & Chow, S. S. M. (2019) · IEEE Transactions on Dependable and Secure Computing · doi:10.1109/tdsc.2019.2940020 · Cited by 40 · see citing works
Systematizing Genome Privacy Research: A Privacy-Enhancing Technologies Perspective
Mittos, A., Malin, B., & Cristofaro, E. D. (2018) · Proceedings on Privacy Enhancing Technologies · doi:10.2478/popets-2019-0006 · Cited by 42 · see citing works
Wang, G., Lu, R., & Guan, Y. L. (2019) · IEEE Access · doi:10.1109/access.2019.2891775 · Cited by 39 · see citing works
Profiling tax and financial behaviour with big data under the GDPR
Politou, E., Alepis, E., & Patsakis, C. (2019) · Computer law & security review · doi:10.1016/j.clsr.2019.01.003 · Cited by 42 · see citing works
Wang, J., He, D., Castiglione, A., Gupta, B. B., Karuppiah, M., & Wu, L. (2022) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2022.3177755 · Cited by 38 · see citing works
Towards Privacy-Preserving Medical Cloud Computing Using Homomorphic Encryption
Kocabaş, Ö., & Soyata, T. (2015) · Advances in wireless technologies and telecommunication book series · doi:10.4018/978-1-4666-8662-5.ch007 · Cited by 36 · see citing works
Liu, X., Zhu, H., Lu, R., & Li, H. (2016) · Peer-to-Peer Networking and Applications · doi:10.1007/s12083-016-0506-8 · Cited by 36 · see citing works
“Bos et al. [12] presented a working implementation of a prediction service to diagnose the likelihood of contracting a disease by using logistic regression and the Cox proportional hazard model.”
MethodA community effort to protect genomic data sharing, collaboration and outsourcing
Wang, S., Jiang, X., Tang, H., Wang, X., Bu, D., Carey, K., Dyke, S. O. M., Fox, D., Jiang, C., Lauter, K., et al. (2017) · npj Genomic Medicine · doi:10.1038/s41525-017-0036-1 · Cited by 36 · see citing works
Privacy-Enhancing Technologies in Biomedical Data Science
Cho, H., Froelicher, D., Dokmai, N., Nandi, A., Sadhuka, S., Hong, M. M., & Berger, B. (2024) · Annual Review of Biomedical Data Science · doi:10.1146/annurev-biodatasci-120423-120107 · Cited by 34 · see citing works
Masta: An HE-Friendly Cipher Using Modular Arithmetic
Ha, J., Kim, S., Choi, W., Lee, J., Moon, D., Yoon, H., & Cho, J. (2020) · IEEE Access · doi:10.1109/access.2020.3033564 · Cited by 35 · see citing works
“Various applications of HE to medical, genomic, and financial tasks have also been proposed [7], [14], [16], [37], [40], [48].”
BackgroundPrivacy-Enhanced Machine Learning with Functional Encryption
Marc, T., Stopar, M., Hartman, J., Bizjak, M., & Modic, J. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-29959-0_1 · Cited by 34 · see citing works
A Scalable and Pragmatic Method for the Safe Sharing of High-Quality Health Data
Praßer, F., Kohlmayer, F., Spengler, H., & Kuhn, K. A. (2017) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2017.2676880 · Cited by 30 · see citing works
Efficient machine learning over encrypted data with non-interactive communication
Park, H., Kim, P., Kim, H., Park, K.-W., & Lee, Y. (2017) · Computer Standards & Interfaces · doi:10.1016/j.csi.2017.12.004 · Cited by 29 · see citing works
“Fisher’s linear discriminant [28] Cox proportional 1 1 Model info.”
BackgroundMethodInfluentialA Privacy-Preserving Online Medical Prediagnosis Scheme for Cloud Environment
Guo, W., Shao, J., Lu, R., Liu, Y., & Ghorbani, A. A. (2018) · IEEE Access · doi:10.1109/access.2018.2866971 · Cited by 30 · see citing works
“[12] used a fully homomorphic cryptosystem to implement a prediagnosis scheme, which is based on the logistic regression and the Cox proportional hazard model.”
BackgroundMethodAccelerating Encrypted Computing on Intel GPUs
Zhai, Y., Ibrahim, M. M. A., Qiu, Y., Boemer, F., Chen, Z., Titov, A., & Lyashevsky, A. (2022) · IEEE International Parallel and Distributed Processing Symposium (IPDPS) · doi:10.1109/ipdps53621.2022.00074 · Cited by 30 · see citing works
Computing Blindfolded on Data Homomorphically Encrypted under Multiple Keys: A Survey
Aloufi, A., Hu, P., Song, Y., & Lauter, K. (2021) · ACM Computing Surveys · doi:10.1145/3477139 · Cited by 41 · see citing works
“Although there are existing works [16, 17, 28, 99] talking about outsourcing homomorphic computations to the cloud, these works assume data is from one owner; hence, encrypted under one public key.”
BackgroundCheon, J. H., Jeong, J., Lee, J., & Lee, K. (2017) · Lecture notes in computer science · doi:10.1007/978-3-319-70278-0_4 · Cited by 28 · see citing works
A Survey of Homomorphic Encryption for Outsourced Big Data Computation
Fun, T. S., & Samsudin, A. (2016) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2016.08.022 · Cited by 27 · see citing works
“…other words, SWHE schemes can be used to support only a small subset of Big Data computations and certain real-world scenarios, such as protecting medical data [115], genomic and bioinformatics data [116-118], wireless sensor data [106], MySQL data [109], and Integer only data [108, 112, 113, 119].”
BackgroundMethodPREMIX: PRivacy-preserving EstiMation of Individual admiXture.
Chen, F., Dow, M. T., Ding, S., Lu, Y., Jiang, X., Tang, H., & Wang, S. (2016) · PubMed Central · Cited by 25 · see citing works
Private Computation on Encrypted Genomic Data.
Lauter, K., López-Alt, A., & Naehrig, M. (2015) · Cited by 25 · see citing works
Euclidean-Distance Based Fuzzy Commitment Scheme for Biometric Template Security
Gilkalaye, B. P., Rattani, A., & Derakhshani, R. R. (2019) · International Workshop on Biometrics and Forensics (IWBF) · doi:10.1109/iwbf.2019.8739177 · Cited by 24 · see citing works
“One solution to this problem is to use a homomorphic encryption scheme [2] [1] that enables conducting basic operations on encrypted data.”
BackgroundPrivate and Efficient Query Processing on Outsourced Genomic Databases
Ghasemi, R., Aziz, M. M. A., Mohammed, N., Dehkordi, M. H., & Jiang, X. (2016) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2016.2625299 · Cited by 24 · see citing works
Kumar, C. U. O., Gajendran, S., Balaji, V., Nhaveen, A., & Balakrishnan, S. S. (2023) · Soft Computing · doi:10.1007/s00500-023-08330-6 · Cited by 23 · see citing works
“Homomorphic encryption (Huang et al. 2017; Bos et al. 2014) plays a role when it is conceivable to use this technology to do machine learning on encrypted data that remains encrypted throughout.”
BackgroundRetracted
- Authors
- Bos, J. W., Lauter, K., & Naehrig, M.
- Affiliations
- Microsoft (United States) (US)
- Corresponding author
- Lauter, Kristin
- Venue
- Journal of Biomedical Informatics
- Publisher
- Elsevier BV
- Published
- 2014-08
- Volume
- 50
- Pages
- 234-243
- ISSN
- 1532-0464 (ISSN-L)
- OpenAlex
- W2077905990
- Cited by
- 283
- References
- 44
- Citations by year
- 2026: 8 · 2025: 16 · 2024: 24 · 2023: 21 · 2022: 16 · 2021: 23 · 2020: 21 · 2019: 36 · 2018: 31 · 2017: 27 · 2016: 31 · 2015: 25 · 2014: 4
- FWCI
- 28.91
- Type
- journal article
- Language
- en
- Open access
- bronze
- doi.org
- Licence
- Locations
- Journal of Biomedical Informatics (publishedVersion)
- PubMed (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Cryptography and Data Security
- Physical Sciences › Computer Science › Information Systems › Cloud Data Security Solutions
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- homomorphic encryption, cardiovascular disease prediction, health data privacy, Microsoft Azure
- MeSH terms
- Proportional Hazards Models, Medical Records Systems, Computerized, Computer Security, Privacy
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
