9 papers
When Do Differentially Private Inputs Protect Graph Shift Operators?
Andrew Campbell, Chenyue Zhang, Hang Liu +3
We study the differential privacy (DP) of a graph shift operator (GSO) when an analyst observes the output of a graph filter. In particular, we study the setting in which the input…
Reconstruction Limits for Repeated Differentially Private Aggregates: A Cramer-Rao Perspective on Query Geometry
Chenyue Zhang, Andrew Campbell, Anna Scaglione +1
Repeated differentially private (DP) releases are often evaluated by transcript length or cumulative privacy accounting. We show that these quantities do not by themselves determin…
Enabling Safety-Critical Wireless Communications via Safe Reinforcement Learning
Haoran Peng, Tong Wu, Hang Liu +3
Ensuring strict safety guarantees is the paramount challenge for emerging 5G/6G wireless systems, particularly as they increasingly govern mission-critical applications ranging fro…
Differential Privacy of Network Parameters from a System Identification Perspective
Andrew Campbell, Anna Scaglione, Hang Liu +3
This paper addresses the problem of protecting network information from privacy system identification (SI) attacks when sharing cyber-physical system simulations. We model analyst…
Decentralized Differentially Private Power Method
Andrew Campbell, Anna Scaglione, Sean Peisert
We propose a novel Decentralized Differentially Private Power Method (D-DP-PM) for performing Principal Component Analysis (PCA) in networked multi-agent settings. Unlike conventio…
Differentially Private Distribution Release of Gaussian Mixture Models via KL-Divergence Minimization
Hang Liu, Anna Scaglione, Sean Peisert
Gaussian Mixture Models (GMMs) are widely used statistical models for representing multi-modal data distributions, with numerous applications in data mining, pattern recognition, d…
Shuffled Linear Regression via Spectral Matching
Hang Liu, Anna Scaglione
Shuffled linear regression (SLR) seeks to estimate latent features through a linear transformation, complicated by unknown permutations in the measurement dimensions. This problem…
Compressed and Sparse Models for Non-Convex Decentralized Learning
Andrew Campbell, Hang Liu, Leah Woldemariam +1
Recent research highlights frequent model communication as a significant bottleneck to the efficiency of decentralized machine learning (ML), especially for large-scale and over-pa…
Low-Complexity Vector Source Coding for Discrete Long Sequences with Unknown Distributions
Leah Woldemariam, Hang Liu, Anna Scaglione
In this paper, we propose a source coding scheme that represents data from unknown distributions through frequency and support information. Existing encoding schemes often compress…