Privacy-Preserving Multivariate Statistical Analysis: Linear Regression and Classification

By Wenliang Du, Yunghsiang Sam Han, Shigang Chen. 2004

428 citations recorded by the source corpus.

Multivariate statistical analysis is an important data analysis technique that has found applications in various areas. In this paper, we study some multivariate statistical analysis methods in Secure 2-party Computation (S2C) framework illustrated by the following scenario: two parties, each having a secret data set, want to conduct the statistical analysis on their joint data, but neither party is willing to disclose its private data to the other party or any third party. The current statistical analysis techniques cannot be used directly to support this kind of computation because they require all parties to send the necessary data to a central place. In this paper, We define two Secure 2-party multivariate statistical analysis problems: Secure 2-party Multivariate Linear Regression problem and Secure 2-party Multivariate Classification problem. We have developed a practical security model, based on which we have developed a number of building blocks for solving these two problems.

Subfields: Artificial Intelligence, Management Science and Operations Research, Statistical Learning Theory, 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 Management Science and Operations Research

In Statistical Learning Theory

In Privacy & Security

Citations in the corpus

Federated Machine Learning (2019, methodology): “al knowledge disclosure may be considered acceptable if security guarantees are provided. It is possible to build a security model with SMC under lower security requirement in exchange for efficiency [16]. Recently, studies [46] used SMC framework for training machine learning models with two server”
Privacy-Preserving Distributed Linear Regression on High-Dimensional Data (2017, background): “Early implementations of privacy-preserving linear regression protocols [21, 65] either don’t use formal threat models, or leak additional information beyond the result of the computation.”
The Value of Collaboration in Convex Machine Learning with Differential Privacy (2019, methodology): “In the past, secure multi-party computation has been used in various ML models, such as decision trees [5], regression [6], association rules [7], and clustering [8],”
LOGAN: Membership Inference Attacks Against Generative Models (2017, methodology): “Privacy-enhancing tools based on secure multiparty computation and homomorphic encryption have been proposed to securely train supervised machine learning models, such as decision trees [36], linear regressors [15], and neural networks [9, 14].”
Rmind: A Tool for Cryptographically Secure Statistical Analysis (2016, background): “analysis and regression [5], [6], [7], [8], [9], filtered sums,”
Privacy-Preserving Multiple Linear Regression of Vertically Partitioned Real Medical Datasets (2017, methodology): “The study, known as Privacy-Preserving Data Mining (PPDM), aims to perform a data mining algorithm with preserving confidentiality of datasets [3], [4], [6], [7], [8], [9].”
Federated Multi-view Learning for Private Medical Data Integration and Analysis (2021, methodology): “Secure methods are also proposed to solve these two problems [15].”
Privacy preservation in federated learning: An insightful survey from the GDPR perspective (2020, methodology): “Indeed, SMC has been employed in numerousML algorithms such as secure two-party computation (S2C) in linear regression [31], Iterative Dichotomiser3 (ID3) decision tree learning algorithm [78], and k-means clustering algorithm for distributed data mining [62].”
Secure Function Evaluation Using an FPGA Overlay Architecture (2017, background): “A series of recent research eﬀorts [4, 6, 11, 27–29] have attempted to address this issue through cryptographic means and, in particular, through secure function evaluation (SFE).”
FedBCD: A Communication-Efficient Collaborative Learning Framework for Distributed Features (2022, background): “Note under this heuristic security definition, when some prior knowledge about the data is known, an adversary may be able to eliminate some alternative solutions or certain derived statistical information may be revealed [32], [33].”
Secure multiple linear regression based on homomorphic encryption (2011, methodology): “We contrast this focused statistical use of masked data with suggestion in the datamining literature of a fundamentally different sort, e.g., Du et al. [6].”
BatchCrypt: Efficient Homomorphic Encryption for Cross-Silo Federated Learning (2020, background): “Devel-opers have to carefully engineer the ML algorithms and divide the computation among parties to ﬁt the MPC paradigm, which may lower the privacy guarantees for better performance [16,42,43].”
Privacy-Preserving Record Linkage (2010, background): “An alternative which results in fast and often simpler protocols is the “weak” security model given in [9] and studied in [37] section 5.”