LIU, Tiantian; YAO, Hongwei; LIN, Feng; WU, Tong; QIN, Zhan; REN, Kui. Eguard: Defending LLM Embeddings Against Inversion Attacks via Text Mutual Information Optimization. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 42, p. 35644–35652, 2026. DOI: 10.1609/aaai.v40i42.40876. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40876. Acesso em: 15 may. 2026.