Li, Xuan, Zhe Yin, Xiaodong Gu, and Beijun Shen. 2026. “Anti-Adversarial Learning: Desensitizing Prompts for Large Language Model”. Proceedings of the AAAI Conference on Artificial Intelligence 40 (38):31787-95. https://doi.org/10.1609/aaai.v40i38.40447.