# Sound Randomized Smoothing in Floating-Point Arithmetics

Source: [Sound Randomized Smoothing in Floating-Point Arithmetics](<https://www.sota2.com/research/paper/68fa6f211e209131cea43e3c>)

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

Data updated: 2025-10-26T01:13:37.852Z

Authors: V\\'aclav Vor\\'a\\v{c}ek, Matthias Hein

Published: 2022-07-14T21:28:04.000Z

## Abstract

Randomized smoothing is sound when using infinite precision. However, we show that randomized smoothing is no longer sound for limited floating-point precision. We present a simple example where randomized smoothing certifies a radius of $1.26$ around a point, even though there is an adversarial example in the distance $0.8$ and extend this example further to provide false certificates for CIFAR10. We discuss the implicit assumptions of randomized smoothing and show that they do not apply to generic image classification models whose smoothed versions are commonly certified. In order to overcome this problem, we propose a sound approach to randomized smoothing when using floating-point precision with essentially equal speed and matching the certificates of the standard, unsound practice for standard classifiers tested so far. Our only assumption is that we have access to a fair coin.

## 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/2207.07209>)

[PDF](<https://arxiv.org/pdf/2207.07209.pdf>)