Local Differential Privacy for Belief Functions

Authors

  • Qiyu Li Renmin University of China
  • Chunlai Zhou Renmin University of China
  • Biao Qin Renmin University of China
  • Zhiqiang Xu Mohamed bin Zayed University of Artificial Intelligence

DOI:

https://doi.org/10.1609/aaai.v36i9.21241

Keywords:

Reasoning Under Uncertainty (RU)

Abstract

In this paper, we propose two new definitions of local differential privacy for belief functions. One is based on Shafer’s semantics of randomly coded messages and the other from the perspective of imprecise probabilities. We show that such basic properties as composition and post-processing also hold for our new definitions. Moreover, we provide a hypothesis testing framework for these definitions and study the effect of "don’t know" in the trade-off between privacy and utility in discrete distribution estimation.

Downloads

Published

2022-06-28

How to Cite

Li, Q., Zhou, C., Qin, B., & Xu, Z. (2022). Local Differential Privacy for Belief Functions. Proceedings of the AAAI Conference on Artificial Intelligence, 36(9), 10025-10033. https://doi.org/10.1609/aaai.v36i9.21241

Issue

Section

AAAI Technical Track on Reasoning under Uncertainty