Randomized smoothing is a defensive technique to achieve enhanced robustness against adversarial examples which are small input perturbations that degrade the performance of neural network models. Conventional randomized smoothing adds random noise with a fixed noise level for every input sample to smooth out adversarial perturbations. This paper proposes a new variational framework that uses a per-sample noise level suitable for each input by introducing a noise level selector. Our experimental results demonstrate enhancement of empirical robustness against adversarial attacks. We also provide and analyze the certified robustness for our sample-wise smoothing method.
@article{arxiv.2407.11844,
title = {Variational Randomized Smoothing for Sample-Wise Adversarial Robustness},
author = {Ryo Hase and Ye Wang and Toshiaki Koike-Akino and Jing Liu and Kieran Parsons},
journal= {arXiv preprint arXiv:2407.11844},
year = {2024}
}