Huang, Y., Luo, T., Guo, H., & Zhang, Y. (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), 5212–5220. https://doi.org/10.1609/aaai.v40i7.37436