Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models 事件

Grounding-Driven Attack: Improving Encoder-based Adversarial Transferability against Large Vision-Language Models arXiv:2602.09431v2 Announce Type: replace-cross Abstract: Large vision-language models (LVLMs) have achieved impressive performance across multimodal tasks, but their reliance on visual inputs exposes them to adversarial threats. Encoder-based attacks provide an efficient alternative to end-to-end optimization by crafting perturbations through the vision encoder alone. However, exis