GARCIA, Robert; LI, Qiang; BAKER, Amy; WU, Fan. Jailbreak-Resilient LLM Agents through Instruction Hierarchy, Input Gating, and Self-Verification. Journal of Information Technology and Informatics Engineering, [S. l.], v. 1, n. 1, p. 12–31, 2024. Disponível em: https://journal.jci.co.id/jitie/article/view/818. Acesso em: 8 oct. 2026.