Enhancing transferability of adversarial examples via rotation‐invariant attacks
Abstract Deep neural networks are vulnerable to adversarial examples. However, existing attacks exhibit relatively low efficacy in generating transferable adversarial examples. Improved transferability to address this issue is proposed via a rotation‐invariant attack method that maximizes the loss f...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Wiley
2022-02-01
|
| Series: | IET Computer Vision |
| Subjects: | |
| Online Access: | https://doi.org/10.1049/cvi2.12054 |