Privacy-Preserving Distributed Linear Regression on High-Dimensional Data
Adrià Gascón,Phillipp Schoppmann,Borja Balle,Mariana Raykova,Jack Doerner,Samee Zahur,David Evans +6 more
- Vol. 2017, Iss: 4, pp 345-364
TLDR
A hybrid multi-party computation protocol that combines Yao’s garbled circuits with tailored protocols for computing inner products is proposed, suitable for secure computation because it uses an efficient fixed-point representation of real numbers while maintaining accuracy and convergence rates comparable to what can be obtained with a classical solution using floating point numbers.Abstract:
We propose privacy-preserving protocols for computing linear regression models, in the setting where the training dataset is vertically distributed among several parties. Our main contribution is a hybrid multi-party computation protocol that combines Yao’s garbled circuits with tailored protocols for computing inner products. Like many machine learning tasks, building a linear regression model involves solving a system of linear equations. We conduct a comprehensive evaluation and comparison of different techniques for securely performing this task, including a new Conjugate Gradient Descent (CGD) algorithm. This algorithm is suitable for secure computation because it uses an efficient fixed-point representation of real numbers while maintaining accuracy and convergence rates comparable to what can be obtained with a classical solution using floating point numbers. Our technique improves on Nikolaenko et al.’s method for privacy-preserving ridge regression (S&P 2013), and can be used as a building block in other analyses. We implement a complete system and demonstrate that our approach is highly scalable, solving data analysis problems with one million records and one hundred features in less than one hour of total running time.read more
Citations
More filters
Information-Theoretically Secure Multi-Party Linear Regression and Logistic Regression
TL;DR: In this paper , the authors present new protocols for privacy-preserving linear regression and logistic regression training based on Shamir's secret sharing scheme, which can protect users from semi-honest and malicious adversaries with information theoretic security.
Posted Content
Privacy Inference Attacks and Defenses in Cloud-based Deep Neural Network: A Survey.
TL;DR: Wang et al. as mentioned in this paper presented the most recent findings of privacy attacks and defenses appeared in cloud-based neural network services, including data manipulation, training, and prediction, and extracted a new theory, called cloud based ML privacy game, to provide a deep understanding of state-of-the-art research.
Posted Content
HOLMES: A Platform for Detecting Malicious Inputs in Secure Collaborative Computation
Journal Article
Funshade: Functional Secret Sharing for Two-Party Secure Thresholded Distance Evaluation
TL;DR: In this article , a two-party computation of various distance metrics (e.g., Hamming distance, Scalar Product) followed by a comparison with a fixed threshold is proposed.
Proceedings ArticleDOI
AgrEvader: Poisoning Membership Inference against Byzantine-robust Federated Learning
TL;DR: AgrEvader as mentioned in this paper proposes a poisoning membership inference attack that maximizes the adversarial impact on the victim samples while circumventing the detection by Byzantine-robust mechanisms, achieving a high attack accuracy of 72.78% on CIFAR-10 and 97.80% on Texas100.
References
More filters
Book
Numerical Optimization
Jorge Nocedal,Stephen J. Wright +1 more
TL;DR: Numerical Optimization presents a comprehensive and up-to-date description of the most effective methods in continuous optimization, responding to the growing interest in optimization in engineering, science, and business by focusing on the methods that are best suited to practical problems.
Book
Machine Learning : A Probabilistic Perspective
TL;DR: This textbook offers a comprehensive and self-contained introduction to the field of machine learning, based on a unified, probabilistic approach, and is suitable for upper-level undergraduates with an introductory-level college math background and beginning graduate students.
Book
The algebraic eigenvalue problem
TL;DR: Theoretical background Perturbation theory Error analysis Solution of linear algebraic equations Hermitian matrices Reduction of a general matrix to condensed form Eigenvalues of matrices of condensed forms The LR and QR algorithms Iterative methods Bibliography.
Book
The Algorithmic Foundations of Differential Privacy
Cynthia Dwork,Aaron Roth +1 more
TL;DR: The preponderance of this monograph is devoted to fundamental techniques for achieving differential privacy, and application of these techniques in creative combinations, using the query-release problem as an ongoing example.