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

Source: [Mitigating the Curse of Dimensionality for Certified Robustness via Dual Randomized Smoothing](<https://www.sota2.com/research/paper/68fa73b21e209131cea5df83>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-26T02:55:12.649Z

Authors: Song Xia, Yi Yu, Xudong Jiang, Henghui Ding

Published: 2024-04-15T08:54:33.000Z

## 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 ${\\ell\_2}$ certified robustness radius provided by RS exhibits a diminishing trend with the expansion of the input dimension $d$, proportionally decreasing at a rate of $1/\\sqrt{d}$. This paper explores the feasibility of providing ${\\ell\_2}$ 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 ${\\ell\_2}$ certified robustness radius for the original input and reveal that DRS attains a superior upper bound on the ${\\ell\_2}$ robustness radius, which decreases proportionally at a rate of $(1/\\sqrt m + 1/\\sqrt n )$ 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 ${\\ell\_2}$ certified robustness baselines of RS on the CIFAR-10 and ImageNet datasets. Code is available at https://github.com/xiasong0501/DRS.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/2404.09586>)

[PDF](<https://arxiv.org/pdf/2404.09586.pdf>)
