Preprint
Jul 2026
Setting the Privacy Budget in Differential Privacy by Bounding Adversaries'Odds of Learning Sensitive Information
An approach to interpreting and setting $\varepsilon$ is presented, in which the practitioner establishes bounds on the posterior odds that adversaries can learn sensitive information, and the practitioner converts these bounds to values of $\varepsilon$.
Ruwimal Y. Pathiraja, Jerome P. Reiter
· 0 citations