statistical privacy

Bayesian Decision-Theoretic Privacy

Christian P. Robert, Full Professor, Department of Applied Mathematics (CEREMADE), Paris Dauphine-PSL University;

Nov 2, 12:00 - 13:00

B3 R5209

Data Privacy statistical privacy bayesian adversial privacy privacy-preserving machine learning privacy-preserving AI bayesian methods

This seminar introduces two Bayesian decision-theoretic frameworks, persuasive privacy and Bayesian adversarial privacy, that quantify statistical privacy by evaluating how data releases influence adversarial beliefs and decisions while offering contextual alternatives to conventional differential privacy.

On the Difficulties of Assessing Statistical Privacy

Christian P. Robert, Full Professor, Department of Applied Mathematics (CEREMADE), Paris Dauphine-PSL University;

Nov 1, 12:00 - 13:00

B9 R2325

Bayesian Statistics statistical privacy privacy bayesian adversial privacy

This distinguished lecture examines the limitations of statistical disclosure control and differential privacy and explores robust, deliberately insufficient statistics combined with Bayesian inference as an alternative approach to protecting individuals in shared data.