Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices

Junhao Dong; Piotr Koniusz; Yifei Zhang; Hao Zhu; Weiming Liu; Xinghua Qu; Yew-Soon Ong

2025 ICML ICML 2025

Improving Zero-Shot Adversarial Robustness in Vision-Language Models by Closed-form Alignment of Adversarial Path Simplices

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Junhao Dong, Piotr Koniusz, Yifei Zhang, Hao Zhu, Weiming Liu, Xinghua Qu, Yew-Soon Ong

Topics

Artificial Intelligence > Core AI > Multimodal Learning Machine Learning > Learning Types > Adversarial Learning Deep Learning > Learning Types > Multimodal Learning

Keywords

adversarial robustness vision-language model zero-shot classification jacobian adversarial path simplices closed-form alignment

Download PDF