Laat
One paper on achiving zero-shot adversarial robustness with multimodal CLIP models is accepted by CVPR 2024. The proposed LAAT method uses language-driven anchors to guide adversarial training of vision models. Read more
One paper on achiving zero-shot adversarial robustness with multimodal CLIP models is accepted by CVPR 2024. The proposed LAAT method uses language-driven anchors to guide adversarial training of vision models. Read more