Machine learning models have demonstrated remarkable success across diverse domains
but remain vulnerable to adversarial attacks. Empirical defence mechanisms often fall short …

Along with recent diffusion models, randomized smoothing has become one of a few
tangible approaches that offers adversarial robustness to models at scale, eg, those of large …

Neural networks (NNs) are known to be vulnerable against adversarial perturbations, and
thus there is a line of work aiming to provide robustness certification for NNs, such as …

Randomized smoothing has recently emerged as an effective tool that enables certification
of deep neural network classifiers at scale. All prior art on randomized smoothing has …

Randomized smoothing is currently considered the state-of-the-art method to obtain
certifiably robust classifiers. Despite its remarkable performance, the method is associated …

The successful incorporation of machine learning models into safety-critical control systems
requires rigorous robustness guarantees. Randomized smoothing remains one of the state …

Deep neural networks are vulnerable to input deformations in the form of vector fields of
pixel displacements and to other parameterized geometric deformations eg translations …

Randomized smoothing is the current state-of-the-art method for producing provably robust
classifiers. While randomized smoothing typically yields robust $\ell_2 $-ball certificates …

Abstract We propose Adaptive Randomized Smoothing (ARS) to certify the predictions of our
test-time adaptive models against adversarial examples. ARS extends the analysis of …

Recent progress in empirical and certified robustness promises to deliver reliable and
deployable Deep Neural Networks (DNNs). Despite that success, most existing evaluations …