2019/03/19 by Kasra Yazdani, Matthew Hale, Yazdani, Kasra +1 · 1 citation
Computer Science · Engineering · #Cryptography and Data Security #FOS: Electrical engineering #FOS: Mathematics #Optimization and Control (math.OC) #Privacy-Preserving Technologies in Data #Systems and Control (eess.SY) #Vehicular Ad Hoc Networks (VANETs) #electronic engineering #information engineering
paper · pdf · doi:10.48550/arxiv.1903.08199
openalex publication_date 2019/03/19 · openalex created_date 2025/10/10 · openalex updated_date 2026/07/28
Differential privacy has emerged as a formal framework for protecting\nsensitive information in control systems. One key feature is that it is immune\nto post-processing, which means that arbitrary post-hoc computations can be\nperformed on privatized data without weakening differential privacy. It is\ntherefore common to filter private data streams. To characterize this setup, in\nthis paper we present error and entropy bounds for Kalman filtering\ndifferentially private state trajectories. We consider systems in which an\noutput trajectory is privatized in order to protect the state trajectory that\nproduced it. We provide bounds on a priori and a posteriori error and\ndifferential entropy of a Kalman filter which is processing the privatized\noutput trajectories. Using the error bounds we develop, we then provide\nguidelines to calibrate privacy levels in order to keep filter error within\npre-specified bounds. Simulation results are presented to demonstrate these\ndevelopments.\n