Q61 — AWS AIF-C01 Ch.3

Question 61 of 100 | ← Chapter 3

Which type of prompt injection attack involves instructing a large language model (LLM) to disregard its structured instructions and produce output related to prohibited or harmful topics?

• A. Input manipulation
• B. Exploiting helpfulness
• C. Ignoring the prompt template ✓
• D. Prompt persona switching

Correct Answer: C. Ignoring the prompt template

Explanation

In prompt injection attacks, 'ignoring the prompt template' specifically refers to attackers instructing the LLM to bypass its predefined structured instructions, thereby generating output related to prohibited or harmful topics. This attack exploits the model’s instruction-following mechanism by tricking it into disregarding built-in safeguards, potentially resulting in malicious content generation or leakage of restricted information. View all