Трофімов Oleksandr; HULAK, Hennadii. Method for enhancing the robustness of large language models against adversarial attacks. Ukrainian Scientific Journal of Information Security, [S. l.], v. 32, n. 2, p. 72–82, 2026. DOI: 10.18372/2225-5036.32.21660. Disponível em: https://jrnl.kai.edu.ua/index.php/Infosecurity/article/view/21660. Acesso em: 2 nov. 2026.