Two Views of Constrained Differential Privacy: Belief Revision and Update

Authors

  • Likang Liu Renmin University of China
  • Keke Sun Renmin University of China
  • Chunlai Zhou Renmin University of China
  • Yuan Feng University of Technology Sydney

DOI:

https://doi.org/10.1609/aaai.v37i5.25793

Keywords:

KRR: Reasoning with Beliefs, KRR: Belief Change, PEAI: Privacy and Security

Abstract

In this paper, we provide two views of constrained differential private (DP) mechanisms. The first one is as belief revision. A constrained DP mechanism is obtained by standard probabilistic conditioning, and hence can be naturally implemented by Monte Carlo algorithms. The other is as belief update. A constrained DP is defined according to l2-distance minimization postprocessing or projection and hence can be naturally implemented by optimization algorithms. The main advantage of these two perspectives is that we can make full use of the machinery of belief revision and update to show basic properties for constrained differential privacy especially some important new composition properties. Within the framework established in this paper, constrained DP algorithms in the literature can be classified either as belief revision or belief update. At the end of the paper, we demonstrate their differences especially in utility on a couple of scenarios.

Downloads

Published

2023-06-26

How to Cite

Liu, L., Sun, K., Zhou, C., & Feng, Y. (2023). Two Views of Constrained Differential Privacy: Belief Revision and Update. Proceedings of the AAAI Conference on Artificial Intelligence, 37(5), 6450-6457. https://doi.org/10.1609/aaai.v37i5.25793

Issue

Section

AAAI Technical Track on Knowledge Representation and Reasoning