| Autor: |
Ryota Iijima, Sayaka Shiota, Hitoshi Kiya |
| Jazyk: |
angličtina |
| Rok vydání: |
2024 |
| Předmět: |
|
| Zdroj: |
IEEE Access, Vol 12, Pp 69206-69216 (2024) |
| Druh dokumentu: |
article |
| ISSN: |
2169-3536 |
| DOI: |
10.1109/ACCESS.2024.3400958 |
| Popis: |
Deep neural networks (DNNs) are well known to be vulnerable to adversarial examples (AEs). In previous studies, the use of models encrypted with a secret key was demonstrated to be robust against white-box attacks, but not against black-box ones. In this paper, we propose a novel method using the vision transformer (ViT) that is a random ensemble of encrypted models for enhancing robustness against both white-box and black-box attacks. In addition, a benchmark attack method, called AutoAttack, is applied to models to test adversarial robustness objectively. In experiments, the method was demonstrated to be robust against not only white-box attacks but also black-box ones in an image classification task on the CIFAR-10 and ImageNet datasets. The method was also compared with the state-of-the-art in a standardized benchmark for adversarial robustness, RobustBench, and it was verified to outperform conventional defenses in terms of clean accuracy and robust accuracy. |
| Databáze: |
Directory of Open Access Journals |
| Externí odkaz: |
|
