VYAS, Sanyam; CARON, Alberto; HICKS, Chris; BURNAP, Pete; MAVROUDIS, Vasilios. Beyond Training-time Poisoning: Component-level and Post-training Backdoors in Deep Reinforcement Learning. Proceedings of the AAAI Conference on Artificial Intelligence, [S. l.], v. 40, n. 31, p. 26072–26080, 2026. DOI: 10.1609/aaai.v40i31.39809. Disponível em: https://ojs.aaai.org/index.php/AAAI/article/view/39809. Acesso em: 7 may. 2026.