paper-with-me

홈 › Papers

On InstaHide, Phase Retrieval, and Sparse Matrix Factorization

2020-11-23 · Sitan Chen, Xiaoxiao Li, Zhao Song, Danyang Zhuo

In this work, we examine the security of InstaHide, a scheme recently proposed by [Huang, Song, Li and Arora, ICML'20] for preserving the security of private datasets in the context of distributed learning. To generate a synthetic training example to be shared among the distributed learners, InstaHide takes a convex combination of private feature vectors and randomly flips the sign of each entry of the resulting vector with probability 1/2. A salient question is whether this scheme is secure in any provable sense, perhaps under a plausible hardness assumption and assuming the distributions generating the public and private data satisfy certain properties. We show that the answer to this appears to be quite subtle and closely related to the average-case complexity of a new multi-task, missing-data version of the classic problem of phase retrieval. Motivated by this connection, we design a provable algorithm that can recover private vectors using only the public vectors and synthetic vectors generated by InstaHide, under the assumption that the private and public vectors are isotropic Gaussian.

📄 PDF Abstract BibTeX arXiv:2011.11181

Code (0)

등록된 구현이 없습니다.

Tasks

Retrieval

Similar Papers 제목 키워드 기반

Provable Burer-Monteiro factorization for a class of norm-constrained matrix problems

2016-06-04 · Dohyung Park, Anastasios Kyrillidis, Srinadh Bhojanapalli, Constantine Caramanis 외

We study the projected gradient descent method on low-rank matrix problems with a strongly convex objective. We use the Burer-Monteiro factorization approach to implicitly enforce low-rankness; such factorization introdu…

LEMMAQuantum State TomographyRetrieval

What Can Phase Retrieval Tell Us About Private Distributed Learning?

2021-01-01 · ICLR 2021 1 · Sitan Chen, Xiaoxiao Li, Zhao Song, Danyang Zhuo

In this work, we examine the security of InstaHide, a scheme recently proposed by \cite{hsla20} for preserving the security of private datasets in the context of distributed learning. To generate a synthetic training exa…

Retrieval

Dictionary Learning Phase Retrieval from Noisy Diffraction Patterns

2018-10-18

This paper proposes a novel algorithm for image phase retrieval, i.e., for recovering complex-valued images from the amplitudes of noisy linear combinations (often the Fourier transform) of the sought complex images. The…

Dictionary LearningregressionRetrieval

Symmetry, Saddle Points, and Global Optimization Landscape of Nonconvex Matrix Factorization

2016-12-29 · Xingguo Li, Junwei Lu, Raman Arora, Jarvis Haupt 외

We propose a general theory for studying the \xl{landscape} of nonconvex \xl{optimization} with underlying symmetric structures \tz{for a class of machine learning problems (e.g., low-rank matrix factorization, phase ret…

global-optimizationRetrieval

Approximate Method of Variational Bayesian Matrix Factorization/Completion with Sparse Prior

2018-03-14 · Ryota Kawasumi, Koujin Takeda

We derive analytical expression of matrix factorization/completion solution by variational Bayes method, under the assumption that observed matrix is originally the product of low-rank dense and sparse matrices with addi…

Matrix Completion