Year: 2019
Type: preprint
Abstract: Privacy concerns with sensitive data are receiving increasing attention. In this paper, we study local differential privacy (LDP) in interactive decentralized optimization. By constructing random local aggregators, we propose a framework to amplify LDP by a constant. We take Alternating Direction Method of Multipliers (ADMM), and decentralized gradient descent as two concrete examples, where experiments support our theory. In an asymptotic view, we address the following question: Under LDP, is it possible to design a distributed private minimizer for arbitrary closed convex constraints with utility loss not explicitly dependent on dimensionality? As an affiliated result, we also show that with merely linear secret sharing, information theoretic privacy is achievable for bounded colluding agents.
Source: arXiv (Cornell University)
Authors: Xiao, Hanshen, Ye, Yu, Devadas, Srinivas
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2946846162