# Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser

Source: [Certified Zeroth-order Black-Box Defense with Robust UNet Denoiser](<https://www.sota2.com/research/paper/68fa740b1e209131cea5f6f0>)

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

Data updated: 2025-10-28T13:57:07.915Z

Authors: Astha Verma, A V Subramanyam, Siddhesh Bangar, Naman Lal, Rajiv Ratn Shah, Shin'ichi Satoh

Published: 2023-04-13T11:57:06.000Z

## Abstract

Certified defense methods against adversarial perturbations have been recently investigated in the black-box setting with a zeroth-order (ZO) perspective. However, these methods suffer from high model variance with low performance on high-dimensional datasets due to the ineffective design of the denoiser and are limited in their utilization of ZO techniques. To this end, we propose a certified ZO preprocessing technique for removing adversarial perturbations from the attacked image in the black-box setting using only model queries. We propose a robust UNet denoiser (RDUNet) that ensures the robustness of black-box models trained on high-dimensional datasets. We propose a novel black-box denoised smoothing (DS) defense mechanism, ZO-RUDS, by prepending our RDUNet to the black-box model, ensuring black-box defense. We further propose ZO-AE-RUDS in which RDUNet followed by autoencoder (AE) is prepended to the black-box model. We perform extensive experiments on four classification datasets, CIFAR-10, CIFAR-10, Tiny Imagenet, STL-10, and the MNIST dataset for image reconstruction tasks. Our proposed defense methods ZO-RUDS and ZO-AE-RUDS beat SOTA with a huge margin of $35\\%$ and $9\\%$, for low dimensional (CIFAR-10) and with a margin of $20.61\\%$ and $23.51\\%$ for high-dimensional (STL-10) datasets, respectively.

## 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/2304.06430>)

[PDF](<https://arxiv.org/pdf/2304.06430.pdf>)
