Boosting adversarial transferability in vision-language models via multimodal feature heterogeneity
Abstract Vision-language pre-training models have achieved significant success in the field of medical imaging but have exhibited vulnerability to adversarial examples. Although adversarial attacks are harmful, they are valuable in revealing the weaknesses of VLP models and enhancing their robustnes...
Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2025-03-01
|
| Series: | Scientific Reports |
| Online Access: | https://doi.org/10.1038/s41598-025-91802-6 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|