Li X, Yin Z, Gu X, Shen B. Anti-adversarial Learning: Desensitizing Prompts for Large Language Model. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 19];40(38):31787-95. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40447