Two Views of Constrained Differential Privacy: Belief Revision and Update
Keywords:KRR: Reasoning with Beliefs, KRR: Belief Change, PEAI: Privacy and Security
AbstractIn 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.
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
AAAI Technical Track on Knowledge Representation and Reasoning