Huang, Y. et al. 2026. Text-Guided Gradient Refinement: Resolving Multimodal Gradient Conflicts to Boost Adversarial Attacks on Vision-Language Models. Proceedings of the AAAI Conference on Artificial Intelligence. 40, 7 (Mar. 2026), 5212–5220. DOI:https://doi.org/10.1609/aaai.v40i7.37436.