Câu 105: Isaca Advanced in AI Audit

A generative AI system has a validation control in place to reject inappropriate questions by checking them against built-in ethical standards. Which of the following enables malicious actors to circumvent this control through prompt engineering?

1. A. Presenting theoretical situations to justify the reason for asking the questions — đáp án hiện tại
2. B. Submitting the same questions in a foreign language translated by another AI-based system
3. C. Randomly placing keywords unrelated to the main topic
4. D. Asking the same questions later when the algorithm has changed after further learning