# Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing

Source: [Effects of Exponential Gaussian Distribution on (Double Sampling) Randomized Smoothing](<https://www.sota2.com/research/paper/68fa73711e209131cea5c856>)

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

Data updated: 2025-10-26T02:50:15.439Z

Authors: Youwei Shu, Xi Xiao, Derui Wang, Yuxin Cao, Siji Chen, Jason Xue, Linyi Li, Bo Li

Published: 2024-06-04T13:41:00.000Z

## Abstract

Randomized Smoothing (RS) is currently a scalable certified defense method providing robustness certification against adversarial examples. Although significant progress has been achieved in providing defenses against $\\ell\_p$ adversaries, the interaction between the smoothing distribution and the robustness certification still remains vague. In this work, we comprehensively study the effect of two families of distributions, named Exponential Standard Gaussian (ESG) and Exponential General Gaussian (EGG) distributions, on Randomized Smoothing and Double Sampling Randomized Smoothing (DSRS). We derive an analytic formula for ESG's certified radius, which converges to the origin formula of RS as the dimension $d$ increases. Additionally, we prove that EGG can provide tighter constant factors than DSRS in providing $\\Omega(\\sqrt{d})$ lower bounds of $\\ell\_2$ certified radius, and thus further addresses the curse of dimensionality in RS. Our experiments on real-world datasets confirm our theoretical analysis of the ESG distributions, that they provide almost the same certification under different exponents $\\eta$ for both RS and DSRS. In addition, EGG brings a significant improvement to the DSRS certification, but the mechanism can be different when the classifier properties are different. Compared to the primitive DSRS, the increase in certified accuracy provided by EGG is prominent, up to 6.4% on ImageNet.

## 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/2406.02309>)

[PDF](<https://arxiv.org/pdf/2406.02309.pdf>)
