mlsanityData to 7 Oct 2026

Enhanced Security against Adversarial Examples Using a Random Ensemble of Encrypted Vision Transformer Models

arXiv 2307.13985 ↗First posted 26 Jul 2023cs.CR cs.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, which means AEs generated for a source model can fool another black-box model (target model) with a non-trivial probability. In previous studies, it was confirmed that the vision transformer (ViT) is more robust against the property of adversarial transferability than convolutional neural network (CNN) models such as ConvMixer, and moreover encrypted ViT is more robust than ViT without any encryption. In this article, we propose a random ensemble of encrypted ViT models to achieve much more robust models. In experiments, the proposed scheme is verified to be more robust against not only black-box attacks but also white-box ones than convention methods.

Key facts. Cited by 4 papers in the map (data through 7 Oct 2026). Builds on 18 of its 19 references that are in the map. First posted on arXiv 26 Jul 2023.

Builds on

18 of 19 references.

References · 18

  1. 2014Explaining and Harnessing Adversarial Examplescited by 7,287
  2. 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,326
  3. 2016Towards Evaluating the Robustness of Neural Networkscited by 2,976
  4. 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,510
  5. 2020Reliable evaluation of adversarial robustness with an ensemble of diverse parameter-free attackscited by 1,442
  6. 2015DeepFool: a simple and accurate method to fool deep neural networkscited by 1,315
  7. 2016Adversarial Machine Learning at Scalecited by 934
  8. 2019Square Attack: a query-efficient black-box adversarial attack via random searchcited by 682
  9. 2019Unlabeled Data Improves Adversarial Robustnesscited by 415
  10. 2019Minimally distorted Adversarial Examples with a Fast Adaptive Boundary Attackcited by 333
  11. 2019Improving Adversarial Robustness via Promoting Ensemble Diversitycited by 213
  12. 2020DVERGE: Diversifying Vulnerabilities for Enhanced Robust Generation of Ensemblescited by 73
6 more
  1. 2020Block-wise Image Transformation with Secret Key for Adversarially Robust Defensecited by 30
  2. 2022An Overview of Compressible and Learnable Image Transformation with Secret Key and Its Applicationscited by 29
  3. 2020Encryption Inspired Adversarial Defense for Visual Classificationcited by 17
  4. 2022Privacy-Preserving Image Classification Using Isotropic Networkcited by 17
  5. 2021A Protection Method of Trained CNN Model Using Feature Maps Transformed With Secret Key From Unauthorized Accesscited by 4
  6. 2022On the Transferability of Adversarial Examples between Encrypted Modelscited by 4

Built on by

Cited by year

Citing papers per year: 2023: 2; 2024: 1; 2025: 1.

4 papers.

  1. 2025Seed-Induced Uniqueness in Transformer Models: Subspace Alignment Governs Subliminal Transfercited by 5
  2. 2024A Random Ensemble of Encrypted Vision Transformers for Adversarially Robust Defensecited by 3
  3. 2023Hindering Adversarial Attacks with Multiple Encrypted Patch Embeddingscited by 2
  4. 2023Efficient Key-Based Adversarial Defense for ImageNet by Using Pre-trained Modelcited by 1