
The author proposes a method, PMG-AFT, to enhance zero-shot adversarial robustness by leveraging supervision from pre-trained models and clean examples. This approach aims to retain generalization features while mitigating overfitting.


coremsg

Enhancing-Zero-Shot-Adversarial-Robustness-with-Pre-trained-Model-Guided-Fine-Tuning


Enhancing Zero-Shot Adversarial Robustness with Pre-trained Model Guided Fine-Tuning


title_rewrite


The author explores the sensitivity of text prompts in enhancing adversarial robustness for Vision-Language Models. By proposing Adversarial Prompt Tuning (APT), they demonstrate significant improvements in accuracy and robustness by simply adding one learned word to prompts.


Boosting-Adversarial-Robustness-for-Vision-Language-Models-with-One-Prompt-Word


Boosting Adversarial Robustness for Vision-Language Models with One Prompt Word
