Dual Randomized Smoothing: Beyond Global Noise Variance
Quick summary
arXiv:2512.01782v4 Announce Type: replace-cross Abstract: 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. To break through the glob
Key takeaways
- arXiv:2512.01782v4 Announce Type: replace-cross Abstract: 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.
Why it matters
The importance of “Dual Randomized Smoothing: Beyond Global Noise Variance” will be measured by what changes in practice. User behavior, access conditions, verifiable performance and responsible-use outcomes are the signals worth following.
Member comments