Efficient Adversarial Training via Criticality-Aware Fine-Tuning

ArXi:2604.12780v1 Announce Type: cross Vision Transformer (ViT) models have achieved remarkable performance across various vision tasks, with scalability being a key advantage when applied to large datasets. This scalability enables ViT models to exhibit strong generalization capabilities. However, as the number of parameters increases, the robustness of ViT models to adversarial examples does not scale proportionally. Adversarial