Liu T, Yao H, Lin F, Wu T, Qin Z, Ren K. Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization. AAAI [Internet]. 2026 Mar. 14 [cited 2026 May 15];40(42):35644-52. Available from: https://ojs.aaai.org/index.php/AAAI/article/view/40876