# On the Adversarial Transferability of ConvMixer Models

Source: [On the Adversarial Transferability of ConvMixer Models](<https://www.sota2.com/research/paper/68fa6d731e209131cea3a012>)

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

Data updated: 2025-10-26T00:35:22.648Z

Authors: Ryota Iijima, Miki Tanaka, Isao Echizen, Hitoshi Kiya

Published: 2022-09-19T02:51:01.000Z

## Abstract

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, which means AEs generated for a source model can fool another black-box model (target model) with a non-trivial probability. In this paper, we investigate the property of adversarial transferability between models including ConvMixer, which is an isotropic network, for the first time. To objectively verify the property of transferability, the robustness of models is evaluated by using a benchmark attack method called AutoAttack. In an image classification experiment, ConvMixer is confirmed to be weak to adversarial transferability.

## 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/2209.08724>)

[PDF](<https://arxiv.org/pdf/2209.08724.pdf>)