WANG, Zihan; ZHANG, Rui; LI, Hongwei; FAN, Wenshu; JIANG, Wenbo; ZHAO, Qingchuan; XU, Guowen. ConfGuard: A Simple and Effective Backdoor Detection for Large Language Models. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 42, p. 35829–35837, 2026. DOI: 10.1609/aaai.v40i42.40897. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/40897. Acesso em: 27 may. 2026.