# Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks

Source: [Ensemble of Models Trained by Key-based Transformed Images for Adversarially Robust Defense Against Black-box Attacks](<https://www.sota2.com/research/paper/68fa68bb1e209131cea1dda6>)

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

Data updated: 2025-10-25T22:43:58.904Z

Authors: MaungMaung AprilPyone, Hitoshi Kiya

Published: 2020-11-16T02:48:37.000Z

## Abstract

We propose a voting ensemble of models trained by using block-wise transformed images with secret keys for an adversarially robust defense. Key-based adversarial defenses were demonstrated to outperform state-of-the-art defenses against gradient-based (white-box) attacks. However, the key-based defenses are not effective enough against gradient-free (black-box) attacks without requiring any secret keys. Accordingly, we aim to enhance robustness against black-box attacks by using a voting ensemble of models. In the proposed ensemble, a number of models are trained by using images transformed with different keys and block sizes, and then a voting ensemble is applied to the models. In image classification experiments, the proposed defense is demonstrated to defend state-of-the-art attacks. The proposed defense achieves a clean accuracy of 95.56 % and an attack success rate of less than 9 % under attacks with a noise distance of 8/255 on the CIFAR-10 dataset.

## 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/2011.07697>)

[PDF](<https://arxiv.org/pdf/2011.07697.pdf>)
