A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples
Fuente:
arXiv
Guardado en:
| Autores principales: | , , |
|---|---|
| Formato: | Preprint |
| Publicado: |
2024
|
| Materias: | |
| Acceso en línea: | |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| _version_ | 1866909062661144576 |
|---|---|
| author | Iijima, Ryota Shiota, Sayaka Kiya, Hitoshi |
| author_facet | Iijima, Ryota Shiota, Sayaka Kiya, Hitoshi |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2401_02633 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples Iijima, Ryota Shiota, Sayaka Kiya, Hitoshi Cryptography and Security Computer Vision and Pattern Recognition 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. |
| title | A Random Ensemble of Encrypted models for Enhancing Robustness against Adversarial Examples |
| topic | Cryptography and Security Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2401.02633 |