mlsanityData to 7 Oct 2026

On the Transferability of Adversarial Examples between Encrypted Models

arXiv 2209.02997 ↗First posted 7 Sep 2022cs.CVcited by 4

Not on the map. Why?

Abstract (arXiv)

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.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 21 of its 24 references that are in the map. First posted on arXiv 7 Sep 2022.

Builds on

21 of 24 references.

References · 21

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2020An Image is Worth 16x16 Words: Transformers for Image Recognition at Scalecited by 29,915
  3. 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,267
  4. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  5. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  6. 2013Intriguing properties of neural networkscited by 5,114
  7. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  9. 2017One pixel attack for fooling deep neural networkscited by 579
  10. 2016Delving into Transferable Adversarial Examples and Black-box Attackscited by 530
  11. 2016Transferability in Machine Learning: from Phenomena to Black-Box Attacks using Adversarial Samplescited by 439
  12. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
9 more
  1. 2021On the Robustness of Vision Transformers to Adversarial Examplescited by 167
  2. 2019NATTACK: Learning the Distributions of Adversarial Examples for an Improved Black-Box Attack on Deep Neural Networkscited by 94
  3. 2018Learnable Image Encryptioncited by 33
  4. 2018Encryption-then-Compression Systems using Grayscale-based Image Encryption for JPEG Imagescited by 33
  5. 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
  6. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  7. 2020Block-wise Scrambled Image Recognition Using Adaptation Networkcited by 27
  8. 2020A GAN-Based Image Transformation Scheme for Privacy-Preserving Deep Neural Networkscited by 27
  9. 2020Encryption Inspired Adversarial Defense for Visual Classificationcited by 17

Built on by

Cited by year

Citing papers per year: 2022: 1; 2023: 1; 2024: 2.

4 papers.

  1. 2023Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Modelscited by 4
  2. 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
  3. 2022On the Adversarial Transferability of ConvMixer Modelscited by 0
  4. 2024A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examplescited by 0