HUANG, Yuyang; LUO, Tianzuo; GUO, Hengyuan; ZHANG, Yuren. Text-Guided Gradient Refinement: Resolving Multimodal Gradient Conflicts to Boost Adversarial Attacks on Vision-Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 7, p. 5212–5220, 2026. DOI: 10.1609/aaai.v40i7.37436. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/37436. Acesso em: 11 may. 2026.