Gong Y, Ran D, Liu J, Wang C, Cong T, Wang A, et al. FigStep: Jailbreaking Large Vision-Language Models via Typographic Visual Prompts. AAAI [Internet]. 2025 Apr. 11 [cited 2026 May 10];39(22):23951-9. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/34568