AI RESEARCH
Quadratic Objective Perturbation: Curvature-Based Differential Privacy
arXiv CS.LG
•
ArXi:2605.05905v1 Announce Type: new Objective perturbation is a standard mechanism in differentially private empirical risk minimization. In particular, Linear Objective Perturbation (LOP) enforces privacy by adding a random linear term, while strong convexity and stability are ensured by an additional deterministic quadratic term. However, this approach requires the strong assumption of bounded gradients of the loss function, which excludes many modern machine learning models. In this work, we