Huang Y, Luo T, Guo H, Zhang Y. Text-Guided Gradient Refinement: Resolving Multimodal Gradient Conflicts to Boost Adversarial Attacks on Vision-Language Models. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 11];40(7):5212-20. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/37436