Scalable and Secure Logistic Regression via Homomorphic Encryption

By Yoshinori Aono, Takuya Hayashi, Le Trieu Phong, Lihua Wang. 2016

186 citations recorded by the source corpus.

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

Citations in the corpus

Federated Machine Learning (2019, methodology): “[4] proposed a secure logistic regression protocol using homomorphic encryption.”
Private federated learning on vertically partitioned data via entity resolution and additively homomorphic encryption (2017, methodology): “[2016], Aono et al. [2016]. A vertical data partition requires a more complex and expensive protocol, and therefore is less common. Wu et al. [2013] run logistic regression where one party holds the features and the other holds the labels. Duverle et al. [2015] use the Paillier encryption scheme to ”
Entity Resolution and Federated Learning get a Federated Resolution (2018, methodology): “Taylor losses have been used in secure federated learning [1, 12].”
A Quasi-Newton Method Based Vertical Federated Learning Framework for Logistic Regression (2019, methodology): “To address this issue, we will adopt the Taylor approximation for the loss function is proposed in [8, 14] as Taylor loss: l(w;xi, yi) ≈ log 2− 1 2 yiw xi + 1”
Privacy and Robustness in Federated Learning: Attacks and Defenses (2020, methodology): “Privacy-preserving techniques Existing Works Homomorphic Encryption [81], [82]”
SecureML: A System for Scalable Privacy-Preserving Machine Learning (2017, background): “[10] consider a different security model where an”
Secure Logistic Regression Based on Homomorphic Encryption: Design and Evaluation (2018, methodology): “Additive homomorphic encryption Logistic regression Aono et al [16]”
ABY3: A Mixed Protocol Framework for Machine Learning (2018, background): “[8] consider a different security model where an untrusted server col-”
Privacy-preserving logistic regression training (2018, background): “Aono et al. [3] also explored secure logistic regression via homomorphic encryption.”
Privacy-Preserving Support Vector Machine Training Over Blockchain-Based Encrypted IoT Data in Smart Cities (2019, background): “a single type of computation [16], [17].”
Privacy-Preserving Deep Learning via Additively Homomorphic Encryption (2018, methodology): “Making use of only additively homomorphic encryption, privacy-preserving linear/logistic regression systems have been proposed in [7, 8, 10].”
Logistic regression model training based on the approximate homomorphic encryption (2018, methodology): “Aono et al. [11] and Xie et al. [12] used an additive HE scheme to aggregate some intermediate statistics.”
PrivLogit: Efficient Privacy-preserving Logistic Regression by Tailoring Numerical Optimizers (2016, background): “Other works approximate the logistic function, resulting in accuracy loss [Nardi et al., 2012, El Emam et al., 2013, Aono et al., 2016].”
Parallel Distributed Logistic Regression for Vertical Federated Learning without Third-Party Coordinator (2019, methodology): “Kone č n ý et al. [2016] studied the federated optimization problem for this setting where communication efficiency is of the utmost importance and minimizing the number of rounds of communication is the principal goal.”