# Divide, Denoise, and Defend against Adversarial Attacks

Source: [Divide, Denoise, and Defend against Adversarial Attacks](<https://www.sota2.com/research/paper/68fa65ab1e209131cea0bd00>)

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

Data updated: 2025-10-25T21:32:37.817Z

Authors: Seyed-Mohsen Moosavi-Dezfooli, Ashish Shrivastava, Oncel Tuzel

Published: 2018-02-19T19:01:56.000Z

## Abstract

Deep neural networks, although shown to be a successful class of machine learning algorithms, are known to be extremely unstable to adversarial perturbations. Improving the robustness of neural networks against these attacks is important, especially for security-critical applications. To defend against such attacks, we propose dividing the input image into multiple patches, denoising each patch independently, and reconstructing the image, without losing significant image content. We call our method D3. This proposed defense mechanism is non-differentiable which makes it non-trivial for an adversary to apply gradient-based attacks. Moreover, we do not fine-tune the network with adversarial examples, making it more robust against unknown attacks. We present an analysis of the tradeoff between accuracy and robustness against adversarial attacks. We evaluate our method under black-box, grey-box, and white-box settings. On the ImageNet dataset, our method outperforms the state-of-the-art by 19.7% under grey-box setting, and performs comparably under black-box setting. For the white-box setting, the proposed method achieves 34.4% accuracy compared to the 0% reported in the recent works.

## 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/1802.06806>)

[PDF](<https://arxiv.org/pdf/1802.06806.pdf>)
