Трофімов O, Hulak H. Method for enhancing the robustness of large language models against adversarial attacks. Bezpeka ìnf. [Internet]. 2026 Aug. 21 [cited 2026 Nov. 3];32(2):72-8. Available from: https://jrnl.kai.edu.ua/index.php/Infosecurity/article/view/21660