Exam AWS Certified AI Practitioner AIF-C01 topic 1 question 166 discussion

Exam question from Amazon's AWS Certified AI Practitioner AIF-C01

Question #: 166
Topic #: 1

[All AWS Certified AI Practitioner AIF-C01 Questions]

Which scenario describes a potential risk and limitation of prompt engineering in the context of a generative AI model?

A. Prompt engineering does not ensure that the model always produces consistent and deterministic outputs, eliminating the need for validation.
B. Prompt engineering could expose the model to vulnerabilities such as prompt injection attacks.
C. Properly designed prompts reduce but do not eliminate the risk of data poisoning or model hijacking.
D. Prompt engineering does not ensure that the model will consistently generate highly reliable outputs when working with real-world data.

Show Suggested Answer

Suggested Answer: B 🗳️

by Rcosmos at June 6, 2025, 1:27 p.m.

Disclaimers:

- ExamTopics website is not related to, affiliated with, endorsed or authorized by Amazon.
- Trademarks, certification & product names are used for reference only and belong to Amazon.

Comments

Submit Cancel

65703c1

2 weeks, 6 days ago

Selected Answer: B

B is the correct answer

upvoted 1 times

...

Engenharia de prompt (ou engenharia imediata) é o processo de projetar instruções (prompts) para orientar a saída de um modelo de IA generativa. No entanto, isso pode introduzir riscos de segurança, especialmente quando o modelo aceita entradas de usuários: Um exemplo clássico é o ataque por injeção de prompt (prompt injection attack), onde o usuário maliciosamente insere comandos que "quebram" ou redirecionam a lógica original do prompt, levando o modelo a fornecer respostas incorretas, perigosas ou sensíveis.

upvoted 2 times

...