A company is building a hiring AI system. The training data contains historical hiring decisions, which may reflect past biases. The team wants to ensure the model does not discriminate against protected groups. Which technique should they use to validate the training data?

Metamorphic testing to verify consistency

Bias detection using statistical parity and disparate impact analysis

Cross-validation to assess model generalization

Data profiling to check for missing values

What is a key difference between black-box and white-box testing for AI-based systems?

Black-box testing requires the tester to know the training data

Black-box testing does not require access to the internal model structure, while white-box testing does

Black-box testing is always more effective than white-box testing for AI systems

White-box testing can only be applied to non-AI systems

A startup is developing a recommendation system using a pre-trained language model provided by a third party. They do not have access to the model's training data or internal parameters. They need to test the system's behavior across various user inputs. Which testing approach is most appropriate?

Mutation testing on the model's code

White-box testing using the model's weights

Grey-box testing using partial knowledge of the architecture

Black-box testing with a diverse set of input prompts

Certified Tester AI Testing

Domain 9Objective 8

Selecting Test Techniques for AI-Based Systems CT-AI Practice Questions (Page 6)

Part of the Domain 9: Methods and Techniques for the Testing of AI-Based Systems domain, which makes up ~13% of our current practice bank. ISTQB does not publish an official question count, but from its 60-minute exam (~25–40 total, ~3–5 in this domain), expect 1–1 from this objective — we provide 31 practice questions to prepare you well beyond it. (estimate)

31questions here

7free pages

7concepts

Questions 26–30

26application · medium
A company is building a hiring AI system. The training data contains historical hiring decisions, which may reflect past biases. The team wants to ensure the model does not discriminate against protected groups. Which technique should they use to validate the training data?
Select an answer first
27foundation · easy
Which technique is specifically used to detect bias in training data for an AI system?
Select an answer first
28foundation · easy
What is a key difference between black-box and white-box testing for AI-based systems?
Select an answer first
29application · easy
A startup is developing a recommendation system using a pre-trained language model provided by a third party. They do not have access to the model's training data or internal parameters. They need to test the system's behavior across various user inputs. Which testing approach is most appropriate?
Select an answer first
30foundation · easy
Which testing approach is most applicable when the internal logic of an AI model is accessible and can be inspected?
Select an answer first

Finished these 5 questions?

Review the revealed explanations, or continue through the curriculum.

Next 5 questions →Back to CT-AI

Free Basic Practice is a study aid with revealable answers — not a scored exam. Examers.io is independent and not affiliated with or endorsed by ISTQB. “CT-AI” is a trademark of its owner, used for identification only.

Selecting Test Techniques for AI-Based Systems CT-AI Practice Questions (Page 6)

Questions 26–30

A company is building a hiring AI system. The training data contains historical hiring decisions, which may reflect past biases. The team wants to ensure the model does not discriminate against protected groups. Which technique should they use to validate the training data?

Which technique is specifically used to detect bias in training data for an AI system?

What is a key difference between black-box and white-box testing for AI-based systems?

A startup is developing a recommendation system using a pre-trained language model provided by a third party. They do not have access to the model's training data or internal parameters. They need to test the system's behavior across various user inputs. Which testing approach is most appropriate?

Which testing approach is most applicable when the internal logic of an AI model is accessible and can be inspected?

Keep studying — Domain 9: Methods and Techniques for the Testing of AI-Based Systems