Variational Randomized Smoothing for Sample-Wise Adversarial Robustness

Autor:	Hase, Ryo, Wang, Ye, Koike-Akino, Toshiaki, Liu, Jing, Parsons, Kieran
Rok vydání:	2024
Předmět:	Computer Science - Machine Learning Computer Science - Artificial Intelligence Computer Science - Cryptography and Security Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Comment: 20 pages, under preparation
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2407.11844 Zobrazit plný text záznamu View this record from Arxiv