Generalised Likelihood Ratio Testing Adversaries through the Differential Privacy Lens
This work addresses the gap between theoretical privacy bounds and practical adversary capabilities in differential privacy, offering incremental improvements for privacy-preserving data analysis.
The paper tackles the problem of overly conservative privacy guarantees in differential privacy by relaxing the assumption of an optimal adversary to a generalized likelihood test adversary, resulting in improved privacy bounds for the Gaussian mechanism that match theoretical upper bounds in numerical evaluations.
Differential Privacy (DP) provides tight upper bounds on the capabilities of optimal adversaries, but such adversaries are rarely encountered in practice. Under the hypothesis testing/membership inference interpretation of DP, we examine the Gaussian mechanism and relax the usual assumption of a Neyman-Pearson-Optimal (NPO) adversary to a Generalized Likelihood Test (GLRT) adversary. This mild relaxation leads to improved privacy guarantees, which we express in the spirit of Gaussian DP and $(\varepsilon, δ)$-DP, including composition and sub-sampling results. We evaluate our results numerically and find them to match the theoretical upper bounds.