DP-epsilon audit

Description

Tight empirical lower bound on the differential-privacy epsilon of a deployed model via membership-inference adversary.

Technical signature

in: (model, canaries[]) → out: { epsilon_lower_bound }

Adversarial robustness

Empirical; pairs with formal DP claims to detect overstated guarantees.

Daubert eligibility

Method is peer-reviewed, has published error rates, and is reproducible from the chain-of-custody hash. Eligible for Tier-A admissibility packaging. Ultimate admissibility is the court's determination.