Black-box certification with randomized smoothing: a functional optimization based framework

Zhang, Dinghuai, Ye, Mao, Gong, Chengyue, Zhu, Zhanxing and Liu, Qiang (2020) Black-box certification with randomized smoothing: a functional optimization based framework. Larochelle, H., Ranzanto, M., Hadsell, R., Balcan, M.F. and Lin, H. (eds.) In Advances in Neural Information Processing Systems 33. Neural Information Processing Systems Foundation..

Abstract

Randomized classifiers have been shown to provide a promising approach for achieving certified robustness against adversarial attacks in deep learning. However, most existing methods only leverage Gaussian smoothing noise and only work for ℓ2 perturbation. We propose a general framework of adversarial certification with non-Gaussian noise and for more general types of attacks, from a unified functional optimization perspective. Our new framework allows us to identify a key trade-off between accuracy and robustness via designing smoothing distributions and leverage it to design new families of non-Gaussian smoothing distributions that work more efficiently for different ℓp settings, including ℓ1, ℓ2 and ℓ∞ attacks. Our proposed methods achieve better certification results than previous works and provide a new perspective on randomized smoothing certification.

This record has no associated files available for download.

Contributors

Download statistics