# On the Transferability of Adversarial Examples between Encrypted Models

Source: [On the Transferability of Adversarial Examples between Encrypted Models](<https://www.sota2.com/research/paper/68fa6d671e209131cea398a1>)

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

Data updated: 2025-10-26T00:33:23.458Z

Authors: Miki Tanaka, Isao Echizen, Hitoshi Kiya

Published: 2022-09-07T08:50:26.000Z

## Abstract

Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In addition, AEs have adversarial transferability, namely, AEs generated for a source model fool other (target) models. In this paper, we investigate the transferability of models encrypted for adversarially robust defense 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, the use of encrypted models is confirmed not only to be robust against AEs but to also reduce the influence of AEs in terms of the transferability of models.

## 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/2209.02997>)

[PDF](<https://arxiv.org/pdf/2209.02997.pdf>)