Machine Learning Classification over Encrypted Data

By Raphael Bost, Raluca Ada Popa, Stephen Tu, Shafi Goldwasser. 2015

773 citations recorded by the source corpus.

Subfields: Computer Networks and Communications, ML Systems & Hardware, Privacy & Security

How researchers see this paper

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

In Computer Networks and Communications

In ML Systems & Hardware

In Privacy & Security

Citations in the corpus

Privacy in Deep Learning: A Survey (2020, methodology): “ARDEN [106] # # # MNIST, CIFAR-10, SVHN Image Classification w/ DNN Cloak [107] # # CIFAR-100, CelebA, UTKFace Image Classification w/ DNN Cryptonets [108] # # # MNIST Image Classification w/ DNN Private Classification [109] # # # MNIST Image Classification w/ DNN TAPAS [110] # # # MNIST, Faces, Can”
SecureBoost: A Lossless Federated Learning Framework (2019, methodology): “, see the works of Bost et al.(32) and Baldimtsi et al.”
Slalom: Fast, Verifiable and Private Execution of Neural Networks in Trusted Hardware (2018, background): “, in the latter two where the computation is performed locally by the data owner), the need for integrity is a common denominator, and this is the property we primarily focus on in this paper (and for which we obtain the best results!) Cryptography can address some of these problems [17, 32, 3, 38, ”
Federated Learning: Challenges, Methods, and Future Directions (2019, background): “We refer interested readers to [7] for a more comprehensive review of the approaches based on homomorphic encryption and SMC.”
Machine Learning Models that Remember Too Much (2017, background): “disclosure of the model to the user [12].”
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).”
Making AI Forget You: Data Deletion in Machine Learning (2019, background): “[16] R.”
CryptoDL: Deep Neural Networks over Encrypted Data (2017, methodology): “In recent years, several studies have investigated the privacy protection of this sensitive data in different machine learning algorithms such as linear regression [39], linear classifiers [5,13], decision trees [5,44] or neural networks [9,49].”
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 [46], linear classifiers [10, 33], and decision trees [11].”
Chameleon: A Hybrid Secure Computation Framework for Machine Learning Applications (2018, neutral): “[19] study privacy-preserving classification based on hyperplane decision, Naive Bayes, and decision trees using homomorphic encryption.”
Privacy-preserving Machine Learning as a Service (2018, neutral): “While privacy-preserving machine learning based on secure multi-party computation techniques have been studied in the literature, those approaches focus on traditional machine learning algorithms such as linear regression [6], decision trees [2, 5, 53] and linear classifiers [5, 19].”
Model inversion attacks against collaborative inference (2019, background): “[4] proposed to encrypt the data before feeding them into the training algorithm.”
Secure SVM Training Over Vertically-Partitioned Datasets Using Consortium Blockchain for Vehicular Social Networks (2020, background): “In the field of VSNs, data are collected by different entities [12, 13] such as vehicular manufacturers, vehicle management agencies, and social network application companies.”
Oblivious Neural Network Predictions via MiniONN Transformations (2017, background): “For general machine learning models, nearly practical solutions have been proposed [6, 14, 15, 58].”
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, methodology): “2 shows the two-party scheme proposed by Bost et al [44]: MLSP holding the key pair sends k encrypted weight vectors to the client in Step 1.”
EPIC: Efficient Private Image Classification (or: Learning from the Masters) (2019, background): “In the 2-PC setting, Bost et al. [6], and Rahulamathavan et al. [41] focus on the problem of private classification, where both the classifier parameters, and the client’s input to be classified need to remain private.”
ML-Leaks: Model and Data Independent Membership Inference Attacks and Defenses on Machine Learning Models (2018, background): “Another relevant line of work is privacy-preserving machine learning [6], [9]–[11], [13], [14], [17], [18], [25], [29].”