CT-AI ISTQB Certified Tester AI Testing Exam Questions and Answers

The syllabus describes automation bias as:

"A type of bias caused by a person favoring the recommendations of an automated decision-making system over other sources."

This is also known as complacency bias, where testers accept automated system outputs without questioning them.

(Reference: ISTQB CT-AI Syllabus v1.0, Glossary, Page 89 of 99)

The syllabus states:

“A/B testing can be used to test updates to an AI-based system where there are agreed acceptance criteria, such as ML functional performance metrics, as described in Chapter 5. A/B testing is used to compare the updated variant with the previous variant.”

(Reference: ISTQB CT-AI Syllabus v1.0, Section 9.4, page 68 of 99)

The syllabus states that non-determinism is one of the key challenges for ensuring safety in AI-based systems:

"The characteristics of AI-based systems that make it more difficult to ensure they are safe... include: complexity, non-determinism, probabilistic nature, self-learning, lack of transparency, interpretability and explainability, and lack of robustness."

(Reference: ISTQB CT-AI Syllabus v1.0, Section 2.8, page 25 of 99)

Pairwise testing is used to handle the large number of combinations of parameters that can arise in complex systems like self-driving cars. The question asks which of the given options isleast likelyto be a reason for the explosion in the number of parameters.

Different Road Types (A): Self-driving cars must operate on various road types, such as highways, city streets, rural roads, etc. Each road type can have different characteristics, requiring the car's system to adapt and handle different scenarios. Thus, this is a significant factor contributing to the growth of parameters.

Different Weather Conditions (B): Weather conditions such as rain, snow, fog, and bright sunlight significantly affect the performance of self-driving cars. The car's sensors and algorithms must adapt to these varying conditions, which adds to the number of parameters that need to be considered.

ML Model Metrics to Evaluate Functional Performance (C): While evaluating machine learning (ML) model performance is crucial, it does not directly contribute to the explosion of parameter combinations in the same way that road types, weather conditions, and car features do. Metrics are used to measure and assess performance but are not themselves variable conditions that the system must handle.

Different Features like ADAS, Lane Change Assistance, etc. (D): Advanced Driver Assistance Systems (ADAS) and other features add complexity to self-driving cars. Each feature can have multiple settings and operational modes, contributing to the overall number of parameters.

Hence, theleast likelyreason for the incredible growth in the number of parameters isC. ML model metrics to evaluate the functional performance.

The ISTQB CT-AI syllabus (Section5.3 – AI Support for Defect Analysis) explains that AI can categorize defect reports using natural language processing or classification models. Categorization helps route defects efficiently and determine which areas of the system are affected. Thus, OptionCis correct: AI canidentify defect categories, supporting assignment and triage.

Option A is incorrect because ML cannot infer severity or consequence without domain-specific risk modeling. Option B inaccurately ties duplicate detection to criticality; the syllabus separatesduplicate detectionfromseverity analysis. Option D is incorrect because AI may assist in routing defects using categories, but the syllabus does not claim AI identifies specific developers.

Thus,Option Cis the syllabus-accurate statement.

The ISTQB CT-AI syllabus (Section3.2 – Model Evaluation) specifies the correct usage oftraining,validation, andtestdatasets. It emphasizes that thetest dataset must be representative of the real operational dataand must beequivalent in distribution to the training and validation sets, ensuring a fair and unbiased evaluation. Option D precisely matches this requirement.

Option A contradicts the syllabus because validation and test sets servedifferent purposes: validation is for tuning, test is for final evaluation. Combining them undermines the reliability of results. Option B is incorrect because even with limited data, the syllabus recommends maintaining a test set or using techniques such ascross-validationrather than eliminating testing. Option C is wrong because equal distribution (33/33/33) isnot recommended; typically, the training set is much larger (e.g., 70–80%).

Thus, OptionDis the only statement aligned with the syllabus' guidance.

Defect prediction models aim to identify parts of the software that are likely to contain defects by analyzing historical data and code quality metrics. The primary goal is to use this predictive information to allocate testing and maintenance resources effectively. Let's break down why option D is the correct choice:

Understanding Classification Models:

Classification models are a type of supervised learning algorithm used to categorize or classify data into predefined classes or labels. In the context of defect prediction, the classification model would classify parts of the code as either "defective" or "non-defective" based on the input features.

Input Data - Code Quality Metrics:

The input data for these classification models typically includes various code quality metrics such as cyclomatic complexity, lines of code, number of methods, depth of inheritance, coupling between objects, etc. These metrics help the model learn patterns associated with defects.

Historical Data:

Historical versions of the code along with their defect records provide the labeled data needed for training the classification model. By analyzing this historical data, the model can learn which metrics are indicative of defects.

Why Option D is Correct:

Option D specifies using a classification model to predict the presence of defects by using code quality metrics as input data. This accurately describes the process of defect prediction using historical bug data and quality metrics.

Eliminating Other Options:

A. Identifying the relationship between developers and the modules developed by them: This does not directly involve predicting defects based on code quality metrics and historical data.

B. Search of similar code based on natural language processing: While useful for other purposes, this method does not describe defect prediction using classification models and code metrics.

C. Clustering of similar code modules to predict based on similarity: Clustering is an unsupervised learning technique and does not directly align with the supervised learning approach typically used in defect prediction models.

The syllabus mentions a drawback of AI-generated test cases:

“AI-based test generation tools can generate test cases… However, unless a test model that defines required behaviors is used as the basis of the tests, this form of test generation generally suffers from a test oracle problem because the AI-based tool does not know what the expected results should be.”

(Reference: ISTQB CT-AI Syllabus v1.0, Section 11.3, page 78 of 99)

The question asks which combination of tests would be most appropriate to include in the strategy for optimal detection in a workflow system using multiple ML models.

Pairwise testing of combinations (I): This method is useful for testing interactions between different components in the workflow to ensure they work well together, identifying potential issues in the integration.

Testing each individual model for accuracy (II): Ensuring that each model in the workflow performs accurately on its own is crucial before integrating them into a combined workflow.

A/B testing of different sequences of models (III): This involves comparing different sequences to determine which configuration yields the best results. While useful, it might not be as fundamental as pairwise and individual accuracy testing in the initial stages.

Detecting biases in the ML pipeline involves various tests to ensure fairness and accuracy throughout the ML process.

Testing the distribution shift in the training data for inappropriate bias (A): This involves checking if there is any shift in the data distribution that could lead to bias in the model. It is an important test but not the most direct method for detecting biases.

Test the model during model evaluation for data bias (B): This is a critical stage where the model is evaluated to detect any biases in the data it was trained on. It directly addresses potential data biases in the model.

Testing the data pipeline for any sources for algorithmic bias (C): This test is crucial as it helps identify biases that may originate from the data processing and transformation stages within the pipeline. Detecting sources of algorithmic bias ensures that the model does not inherit biases from these processes.

Check the input test data for potential sample bias (D): While this is an important step, it focuses more on the input data and less on the overall data pipeline.

Hence, the most likely useful test to help detect different kinds of biases in the ML pipeline isB. Test the model during model evaluation for data bias.

The syllabus states:

“When testing probabilistic and non-deterministic systems, the same input may produce different outputs. Tests need to be run several times to produce statistically valid test results, ensuring that an appropriate number of answers are accurate.”

(Reference: ISTQB CT-AI Syllabus v1.0, Section 8.4, page 58 of 99)

The syllabus defines bias as:

"Bias is the systematic difference in treatment of certain objects, people or groups in comparison to others."

It also discusses:

"Sample bias can occur if the data used for training the model does not represent the operational environment, or if some relevant faulty conditions are excluded deliberately."

(Reference: ISTQB CT-AI Syllabus v1.0, Section 7.6 and 8.3)

When written requirements are given in text documents, the best way to generate test cases is by using Natural Language Processing (NLP). Here's why:

Natural Language Processing (NLP): NLP can analyze and understand human language. It can be used to process textual requirements to extract relevant information and generate test cases. This method is efficient in handling large volumes of textual data and identifying key elements necessary for testing.

Why Not Other Options:

Analyzing source code for generating test cases: This is more suitable for white-box testing where the code is available, but it doesn't apply to text-based requirements.

Machine learning on logs of execution: This approach is used for dynamic analysis based on system behavior during execution rather than static textual requirements.

GUI analysis by computer vision: This is used for testing graphical user interfaces and is not applicable to text-based requirements.

The process of developing a machine learning model typically involves the use of three types of datasets:

Training Data:This is used to train the model, i.e., to learn the patterns and relationships in the data.

Validation Data:This is used to tune the model’s hyperparameters and to prevent overfitting during the training process.

Test Data:This is used to evaluate the final model’s performance and to estimate how it will perform on unseen data.

Let's analyze each option:

A. Training data - validation data - test data

This option correctly includes all three types of datasets used in the process of creating and validating a model. The training data is used for learning, validation data for tuning, and test data for final evaluation.

B. Training data - validation data

This option misses the test data, which is crucial for evaluating the model’s performance on unseen data after the training and validation phases.

C. Training data - test data

This option misses the validation data, which is important for tuning the model and preventing overfitting during training.

D. Validation data - test data

This option misses the training data, which is essential for the initial learning phase of the model.

Therefore, the correct answer isAbecause it includes all necessary datasets used during the process of learning and creating the model: training, validation, and test data​​.

The question asks which characteristic is least likely to cause safety-related issues for an AI system. Let's evaluate each option:

Non-determinism (A): Non-deterministic systems can produce different outcomes even with the same inputs, which can lead to unpredictable behavior and potential safety issues.

Robustness (B): Robustness refers to the ability of the system to handle errors, anomalies, and unexpected inputs gracefully. A robust system is less likely to cause safety issues because it can maintain functionality under varied conditions.

High complexity (C): High complexity in AI systems can lead to difficulties in understanding, predicting, and managing the system's behavior, which can cause safety-related issues.

Self-learning (D): Self-learning systems adapt based on new data, which can lead to unexpected changes in behavior. If not properly monitored and controlled, this can result in safety issues.

Recognizing digits from a scan of handwritten numbers using machine learning is an example of classification. Here’s a breakdown:

Classification: This type of machine learning involves categorizing input data into predefined classes. In this scenario, the input data (handwritten digits) are classified into one of the 10 digit classes (0-9).

Why Not Other Options:

Reinforcement Learning: This involves learning by interacting with an environment to achieve a goal, which does not fit the problem of recognizing digits.

Regression: This is used for predicting continuous values, not discrete categories like digit recognition.

Clustering: This involves grouping similar data points together without predefined classes, which is not the case here.

A. Add 10% of the rows randomly and create another model and compare the R-Square scores of both the models.

Adding more data to the training set can affect the R-Square score, but it does not directly verify the correctness of the implementation.

B. Train various models by changing the order of input features and verify that the R-Square score of these models vary significantly.

Changing the order of input features should not significantly affect the R-Square score if the implementation is correct, but this approach is more about testing model robustness rather than correctness of the implementation.

C. Compare the R-Square score of the model obtained using two different implementations that utilize two different programming languages while using the same algorithm and the same training and testing data.

This approach directly compares the performance of two implementations of the same algorithm. If both implementations produce similar R-Square scores on the same training and testing data, it suggests that the new implementation "X" is correct.

D. Drop 10% of the rows randomly and create another model and compare the R-Square scores of both the models.

Dropping data can lead to variations in the R-Square score but does not directly verify the correctness of the implementation.

Therefore, optionCis the most appropriate strategy because it directly compares the performance of the new implementation "X" with another implementation using the same algorithm and datasets, which helps in verifying the correctness of the implementation​​.

Section2.10 – Explainability and Transparencyof the ISTQB CT-AI syllabus describes explainable AI as the ability of a system to provide human-understandable insight into its decisions. The syllabus referencesThe Royal Society’s reportas a foundational source explaining why explainability is important. Among the stated motivations is the need toincrease user trust and confidencein AI systems by making their decisions understandable and justifiable. Therefore, OptionCdirectly reflects the syllabus content .

Option A is incorrect because interpretability doesnotrefer to determining correctness of outputs; rather, it refers to understandinghowthe model arrives at outputs. Option B incorrectly frames explainability as the ability to investigate algorithms or training data; explainability is aboutunderstanding the model’s decision-making, not reverse engineering its components. Option D is incorrect because explainability doesnoteliminate the need for risk and vulnerability assessments; the syllabus clearly emphasizes that testing, risk assessment, and robustness checks remain critical even when a model is explainable.

Thus, the only statement consistent with the syllabus isOption C.

A. Black box attacks based on adversarial examples create an exact duplicate model of the original.

Black box attacks do not create an exact duplicate model. Instead, they exploit the model by querying it and using the outputs to craft adversarial examples without knowledge of the internal workings.

B. These attack examples cause a model to predict the correct class with slightly less accuracy even though they look like the original image.

Adversarial examples typically cause the model to predict the incorrect class rather than just reducing accuracy. These examples are designed to be visually indistinguishable from the original image but lead to incorrect classifications.

C. These attacks can't be prevented by retraining the model with these examples augmented to the training data.

This statement is incorrect because retraining the model with adversarial examples included in the training data can help the model learn to resist such attacks, a technique known as adversarial training.

D. These examples are model specific and are not likely to cause another model trained on the same task to fail.

Adversarial examples are often model-specific, meaning that they exploit the specific weaknesses of a particular model. While some adversarial examples might transfer between models, many are tailored to the specific model they were generated for and may not affect other models trained on the same task.

Therefore, the correct answer isDbecause adversarial examples are typically model-specific and may not cause another model trained on the same task to fail​​.

Setting model and algorithm hyperparameters is an essential step in the machine learning workflow, primarily occurring during the tuning phase.

Evaluating the model (A): This stage involves assessing the model's performance using metrics and does not typically include the setting of hyperparameters.

Deploying the model (B): Deployment is the stage where the model is put into production and used in real-world applications. Hyperparameters should already be set before this stage.

Tuning the model (C): This is the correct stage where hyperparameters are set. Tuning involves adjusting the hyperparameters to optimize the model's performance.

Data testing (D): Data testing involves ensuring the quality and integrity of the data used for training and testing the model. It does not include setting hyperparameters.

Hence, the most appropriate stage of the ML workflow to set model and algorithm hyperparameters isC. Tuning the model.

Section2.4 – Data Labeling Approachesof the ISTQB CT-AI syllabus explicitly definesAI-assisted data labelingas a hybrid process in which an automated tool performs the initial labeling and human annotators subsequently verify, correct, or complete the labels. This two-step process improves efficiency while retaining human oversight to ensure data quality. The syllabus describes this method as an effective compromise when manual labeling alone would be too slow or costly, and when initial automation can identify obvious patterns before a human provides the final authoritative labels .

Option A (internal labeling) refers to labeling conducted by the organization’s own staff but does not imply automation. Option B (crowdsourced labeling) leverages a distributed workforce, typically without automation. Option C (outsourced labeling) transfers labeling tasks to external vendors but similarly does not involve an AI-first step. Only OptionDreflects the two-stage automated-then-human workflow described in the syllabus.

Therefore,AI-assisted data labeling(Option D) is unequivocally correct.

To calculate the accuracy, recall, and specificity from the confusion matrix provided, we use the following formulas:

Confusion Matrix:

Actually Rotten: 45 (True Positive), 8 (False Positive)

Actually Fresh: 5 (False Negative), 42 (True Negative)

Accuracy:

Accuracy is the proportion of true results (both true positives and true negatives) in the total population.

Formula: Accuracy=TP+TNTP+TN+FP+FN\text{Accuracy} = \frac{TP + TN}{TP + TN + FP + FN}Accuracy=TP+TN+FP+FNTP+TN​

Calculation: Accuracy=45+4245+42+8+5=87100=0.87\text{Accuracy} = \frac{45 + 42}{45 + 42 + 8 + 5} = \frac{87}{100} = 0.87Accuracy=45+42+8+545+42​=10087​=0.87

Recall (Sensitivity):

Recall is the proportion of true positive results in the total actual positives.

Formula: Recall=TPTP+FN\text{Recall} = \frac{TP}{TP + FN}Recall=TP+FNTP​

Calculation: Recall=4545+5=4550=0.9\text{Recall} = \frac{45}{45 + 5} = \frac{45}{50} = 0.9Recall=45+545​=5045​=0.9

Specificity:

Specificity is the proportion of true negative results in the total actual negatives.

Formula: Specificity=TNTN+FP\text{Specificity} = \frac{TN}{TN + FP}Specificity=TN+FPTN​

Calculation: Specificity=4242+8=4250=0.84\text{Specificity} = \frac{42}{42 + 8} = \frac{42}{50} = 0.84Specificity=42+842​=5042​=0.84

Therefore, the correct combinations of accuracy, recall, and specificity are 0.87, 0.9, and 0.84 respectively.

The syllabus mentions that experience-based testing and EDA are effective for detecting biases:

“Experience-based testing can be used to verify that the training dataset is operationally relevant and identify potential sources of bias. EDA is also useful for exploring the data and understanding any relationships that might lead to bias in the model.”

(Reference: ISTQB CT-AI Syllabus v1.0, Section 8.3, page 58 of 99)

The syllabus definesexplainabilityas the ability to understand how the AI-based system comes up with a particular result:

"Explainability is considered to be the ease with which users can determine how the AI-based system comes up with a particular result."

(Reference: ISTQB CT-AI Syllabus v1.0, Section 2.7)

The syllabus states:

"Transparency: This is considered to be the ease with which the algorithm and training data used to generate the model can be determined."

Access to the training data is an example of transparency.

(Reference: ISTQB CT-AI Syllabus v1.0, Section 2.7, page 24 of 99)

The syllabus describes exploratory testing as especially useful when there are poor specifications or test oracle problems:

“Exploratory testing is especially useful when there are poor specifications or test oracle problems, which is often the case for AI-based systems.”

(Reference: ISTQB CT-AI Syllabus v1.0, Section 9.6, page 70 of 99)

Prevalence Rate and Model Performance:

The cancer detection system being developed by "Splendid Healthcare" needs to account for the fact that the type of cancer has a 2% prevalence rate in the population. This indicates that the dataset is highly imbalanced with far fewer positive (cancer) cases compared to negative (normal) cases.

Importance of Recall:

Recall, also known as sensitivity or true positive rate, measures the proportion of actual positive cases that are correctly identified by the model. In medical diagnosis, especially cancer detection, recall is critical because missing a positive case (false negative) could have severe consequences for the patient. Therefore, maximizing recall ensures that most, if not all, cancer cases are detected.

Importance of Precision:

Precision measures the proportion of predicted positive cases that are actually positive. High precision reduces the number of false positives, meaning fewer people will be incorrectly diagnosed with cancer. This is also important to avoid unnecessary anxiety and further invasive testing for those who do not have the disease.

Balancing Recall and Precision:

In scenarios where both false negatives and false positives have significant consequences, it is crucial to balance recall and precision. This balance ensures that the model is not only good at detecting positive cases but also accurate in its predictions, reducing both types of errors.

Accuracy and Specificity:

While accuracy (the proportion of total correct predictions) is important, it can be misleading in imbalanced datasets. In this case, high accuracy could simply result from the model predicting the majority class (normal) correctly. Specificity (true negative rate) is also important, but for a cancer detection system, recall and precision take precedence to ensure positive cases are correctly and accurately identified.

Conclusion:

Therefore, for a cancer detection system with a low prevalence rate, maximizing both recall and precision is crucial to ensure effective and accurate detection of cancer cases.

The ISTQB CT-AI syllabus states in Section2.10 – Explainability, Transparency, and Interpretabilitythat interpretability isuser-dependent, meaning different users understand explanations differently. This is because interpretability depends not only on the ML algorithm but also on the user’s domain knowledge, experience, and expectations. OptionBdirectly reflects this syllabus principle: interpretability testing must consideruser background, and explanations must be comprehensible to the intended user group.

Option A is incorrect because explainability testing requires substantial information about the model, data, and expected behavior—not just exploratory effort. Option C is incorrect because explainability isnotgenerally quantifiable through dynamic testing alone, and the syllabus does not assert model-type specificity in this way. Option D exaggerates LIME’s capabilities. LIME offers approximate local explanations, but cannotpreciselystate root causes; the syllabus emphasizes itslimitationsand that explanations areapproximations, not exact reasons.

Therefore,Option Bis the most syllabus-aligned and correct statement.

The syllabus defines back-to-back testing as a method to compare a modified AI system to the previous version, which is ideal in this scenario:

"Back-to-back testing is performed by comparing the outputs of two systems that are supposed to provide the same outputs, one being a known and trusted system and the other being the test system. This approach can be used to test ML systems after re-training to verify that improvements have not introduced regressions."

(Reference: ISTQB CT-AI Syllabus v1.0, Section 9.3, page 67 of 99)

Section1.6.3 – Reinforcement Learningof the ISTQB CT-AI syllabus states that reinforcement learning (RL) is based on anagent interacting with an environment, performing actions, and receivingrewards or penalties. The core concept is thereward function, which guides the agent’s learning process. The syllabus emphasizes that training in RL isdriven by rewards, and the agent aims to maximize cumulative reward over time. Therefore, OptionCdirectly reflects the correct description: the agent learns by being rewarded for successful actions .

Option A is incorrect because RL doesnotuse labeled data; that applies to supervised learning. Option B contradicts the syllabus definition: RL fundamentallyrequiresinteraction with the environment. Option D is incorrect because the reward function isdefined by humans, not learned by the agent; the agent learns apolicy, not the reward function itself.

Thus, OptionCis the only statement consistent with RL as defined in the syllabus.

The ISTQB CT-AI syllabus explains inSection 4.4 – Experience-Based Testing for AI Systemsthat AI-based systems frequently suffer frominsufficient specifications, unpredictable model behavior, andtest oracle problems, especially when outputs depend on probabilistic or learned patterns. The syllabus explicitly states thatexploratory testingis especially valuable in such contexts because it allows testers to investigate the system interactively, observe unexpected behavior, and evaluate system responses that cannot be fully predicted beforehand. Thus, OptionCaccurately reflects the role and justification of exploratory testing for AI systems.

Option A describes data analysis rather than intuitive test design. Option B is incorrect because checklist-based testing does not dynamically adapt test cases; instead, it follows predetermined checklists. Option D incorrectly defines “tour-based testing”; tours refer to structured exploratory approaches, not biased datasets.

Therefore,Option Cis the syllabus-aligned correct statement.

According to Section4.6 – AI Behaviour Testing (AIB Testing)of the ISTQB CT-AI syllabus, AIB testing is used to evaluate changes in the functional behavior of self-learning systems. The core principle iscomparing pre-change and post-change model behavior using the same test inputs, so that any difference in outputs can be attributed to the model’s learning and not to differences in input data. This directly corresponds to OptionC.

Option A is incorrect because the absence of a test oracle does not justify generating new test cases; AIB relies onreusing identical inputsto detect behavioral drift. Option B is invalid because using different inputs prevents meaningful comparison. Option D is incorrect because comparing with an unrelated non-self-learning system does not allow evaluation of the same model’s behavioral evolution.

Thus, OptionCaccurately represents the correct application of AIB testing: assessing model behavior changes by running identical test inputs before and after learning updates.

The syllabus defines overfitting as:

“Overfitting is when the ML model learns the training data so well that it is unable to generalize to accommodate new data.”

This occurs when the model memorizes the training data, including noise, instead of learning the general patterns.

(Reference: ISTQB CT-AI Syllabus v1.0, Section 3.5.1, page 31 of 99)