ML Confidential: Machine Learning on Encrypted Data

By Thore Graepel, Kristin E. Lauter, Michael Naehrig. 2012

502 citations recorded by the source corpus.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition, Federated & Distributed Learning, 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 Artificial Intelligence

In Computer Vision and Pattern Recognition

In Federated & Distributed Learning

In Privacy & Security

Citations in the corpus

Privacy in Deep Learning: A Survey (2020, methodology): “use a Somewhat HE (SHE) scheme to train Linear Means (LM) and Fisher’s Linear Discriminate (FLD) classifiers [98].”
Privacy-Preserving Distributed Linear Regression on High-Dimensional Data (2017, methodology): “Furthermore, our CGD algorithm can also be used directly to improve other MPC protocols requiring a secure linear system solver [33, 35, 59].”
Privacy-Preserving Ridge Regression on Hundreds of Millions of Records (2013, background): “In such a setting, current FHE schemes [35], [50] are not as efficient as our system.”
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).”
CryptoDL: Deep Neural Networks over Encrypted Data (2017, methodology): “use a somewhat HE scheme to train two machine learning classifiers: Linear Mean and Fisher’s Linear Discriminate (FLD) [13].”
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].”
Gradient-Leaks: Understanding and Controlling Deanonymization in Federated Learning (2018, background): “se adding properly-calibrated random noise via differential privacy [17, 18] mechanisms to achieve a reasonable privacy-utility trade-off. Other alternate countermeasures typically involve encryption [9, 23, 26, 78] or secure multiparty communication [8, 77]. In this work, we propose an alternative ”
cuHE: A Homomorphic Encryption Accelerator Library (2015, background): “in [21] showed that it is possible to execute machine learning algorithms on privatized data.”
SHIELD: Scalable Homomorphic Implementation of Encrypted Data-Classifiers (2015, methodology): “The work on CryptDB [22] used a combination of very simple HE schemes to implement a subset of encrypted SQL queries, and the work on “ML Confidential” [23] implemented simple classification tasks on encrypted data.”
CryptoNets: Applying Neural Networks to Encrypted Data with High Throughput and Accuracy (2016, unknown): “Copyright 2016 by the author(s).”
Privacy-preserving outsourced classification in cloud computing (2017, methodology): “[37] in their work used somewhat homomorphic encryption as the privacy-preserving technique, describing how to implement two binary classification algorithms (Linear Means and Fisher’s Linear Discriminant) over encrypted domain.”
Cheetah: Lean and Fast Secure Two-Party Deep Neural Network Inference (2022, background): “Secure computation of machine learning inference algorithms can perhaps date back to [8,23].”
Understanding and Controlling User Linkability in Decentralized Learning (2018, background): “Other alternate countermeasures typically involve encryption [9, 23, 26, 78] or secure multiparty communication [8, 77].”