Processing math: 100%
Skip to yearly menu bar Skip to main content


Poster

Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing

Song Xia · Yi Yu · Jiang Xudong · Henghui Ding

Halle B #118

Abstract: Randomized Smoothing (RS) has been proven a promising method for endowing an arbitrary image classifier with certified robustness. However, the substantial uncertainty inherent in the high-dimensional isotropic Gaussian noise imposes the curse of dimensionality on RS. Specifically, the upper bound of 2 certified robustness radius provided by RS exhibits a diminishing trend with the expansion of the input dimension d, proportionally decreasing at a rate of 1/d. This paper explores the feasibility of providing 2 certified robustness for high-dimensional input through the utilization of dual smoothing in the lower-dimensional space. The proposed Dual Randomized Smoothing (DRS) down-samples the input image into two sub-images and smooths the two sub-images in lower dimensions. Theoretically, we prove that DRS guarantees a tight 2 certified robustness radius for the original input and reveal that DRS attains a superior upper bound on the 2 robustness radius, which decreases proportionally at a rate of (1/m+1/n) with m+n=d. Extensive experiments demonstrate the generalizability and effectiveness of DRS, which exhibits a notable capability to integrate with established methodologies, yielding substantial improvements in both accuracy and 2 certified robustness baselines of RS on the CIFAR-10 and ImageNet datasets. Code is available at https://github.com/xiasong0501/DRS.

Chat is not available.