Private Predictive Analysis on Encrypted Medical Data

By Joppe W. Bos, Kristin E. Lauter, Michael Naehrig. 2014

317 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computational Theory and Mathematics

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computational Theory and Mathematics

Citations in the corpus

Crypto-Nets: Neural Networks over Encrypted Data (2014, methodology): “…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).”
Efficient Private Statistics with Succinct Sketches (2015, methodology): “Homomorphic encryption based techniques have also been used to perform other machine learning operations on encrypted data, including matrix factorization [56], linear classi-ﬁers [11, 40], and decision trees [12].”
Privacy-preserving deep learning (2015, background): “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].”
cuHE: A Homomorphic Encryption Accelerator Library (2015, background): “in [1] showed how to privately perform predictive analysis tasks on encrypted medical data.”
Cheetah: Optimizing and Accelerating Homomorphic Encryption for Private Inference (2020, unknown): “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].”
A Survey on federated learning* (2020, background): “Nevertheless, the system is not sufficiently secure because the transmission of gradients and partial parameters may lead to indirect privacy leakage [37].”
Private genome analysis through homomorphic encryption (2015, methodology): “[15] applied HE to machine learning, and described how to privately conduct predictive analysis based on an encrypted learned model.”
Privacy-Preserving Classification on Deep Neural Network (2017, background): “They may be classified according to the learning algorithms which are involved: linear regression training or prediction [35], [47], linear classifiers [7], [8], [22], decision trees [8] or neural networks”
Security and Privacy in the Internet of Things (2017, background): “As assumed in most previous work on privacy-preserving “machine-learning-as-a-service” work [44, 43, 154], the user (i.”
Encrypted statistical machine learning: new privacy preserving methods (2015, methodology): “…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…”
Machine Learning Classification over Encrypted Data (2015, background): “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.”
FPGA-Based High-Performance Parallel Architecture for Homomorphic Computing on Encrypted Data (2019, background): “…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],…”
Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation (2018, methodology): “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 homomorph”
Membership Inference Attacks Against Machine Learning Models (2016, methodology): “This also holds for the models trained by computing on encrypted data [4], [6], [35].”
An Overview of Federated Deep Learning Privacy Attacks and Defensive Strategies (2020, methodology): “h a method was proposed by [16] to secure DSGD but may easily be adapted to work on federated averaging. Homomorphic encryption has been proposed as a means to ensure privacy for medical data as-well [66]–[68]. Dowlin et al. [69] proposed an implementation for learning on encrypted data with so-call”
A review of applications in federated learning (2020, background): “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).”
Homomorphic Encryption for Arithmetic of Approximate Numbers (2017, methodology): “8 s of evaluation time of [3,9] without parallelization, respectively.”