When Data Manipulation Meets Attack Goals: An In-depth Survey of Attacks for VLMs
A Dai, X Ma, L Chen, S Li, L Wang - arxiv preprint arxiv:2502.06390, 2025 - arxiv.org
Vision-Language Models (VLMs) have gained considerable prominence in recent years due
to their remarkable capability to effectively integrate and process both textual and visual …
to their remarkable capability to effectively integrate and process both textual and visual …