AI RESEARCH
Dual Randomized Smoothing: Beyond Global Noise Variance
arXiv CS.LG
•
ArXi:2512.01782v3 Announce Type: replace Randomized Smoothing (RS) is a prominent technique for certifying the robustness of neural networks against adversarial perturbations. With RS, achieving high accuracy at small radii requires a small noise variance, while achieving high accuracy at large radii requires a large noise variance. However, the global noise variance used in the standard RS formulation leads to a fundamental limitation: there exists no global noise variance that simultaneously achieves strong performance at both small and large radii.