ISQI ISQI-CT-AI Online Practice Questions and Exam Preparation

ISQI ISQI-CT-AI Online Questions & Answers

• Question 111:

  Which of the following is an example of a clustering problem that can be resolved by unsupervised learning?

  A. Associating shoppers with their shopping tendencies
  B. Grouping individual fish together based on their types of fins
  C. Classifying muffin purchases based on the perceived attractiveness of their packaging
  D. Estimating the expected purchase of cat food after a particularly successful ad campaign
  A. Associating shoppers with their shopping tendencies

  ---

  The ISTQB CT-AI syllabus defines clustering as an unsupervised learning approach in which similarities among input data points are identified in order to group them based on common characteristics or attributes. The syllabus explicitly notes that clustering is often used in marketing scenarios, such as grouping customers according to behavior or tendencies.

  Option A directly matches this definition, as associating shoppers with their shopping tendencies involves identifying natural groupings in customer behavior without predefined labels.

  Option B is incorrect because grouping fish by fin types implies predefined categories, which aligns more with classification than clustering. Option C is also a classification problem, as it involves assigning purchases to predefined categories based on perceived attractiveness. Option D describes a prediction task involving numerical estimation, which is a regression problem rather than clustering.

  Therefore, Option A is the correct example of a clustering problem solvable using unsupervised learning.

• Question 112:

  A team of software testers is attempting to create an AI algorithm to assist in software testing. This team has gone through more than 40 testing iterations and can no longer afford the time required to execute the full regression test suite. They want the algorithm to reduce the amount of testing required, thereby shortening each testing cycle.

  How can an AI-based tool be expected to assist in this reduction?

  A. By using a clustering method to quantify relationships between test cases and assigning each test case to a category
  B. By performing optimization using data from past iterations to identify where defects most frequently occurred and selecting the corresponding test cases
  C. By performing Bayesian analysis to estimate the types of human interactions expected in the system and then selecting those test cases
  D. By using A/B testing to compare the previous update with the newest change and compare metrics between the two
  B. By performing optimization using data from past iterations to identify where defects most frequently occurred and selecting the corresponding test cases

  ---

  The ISTQB CT-AI syllabus explains that AI-based tools can be used to optimize regression test suites by analyzing historical testing information. This includes data from previous test executions, defect history, and recent code or feature changes. By identifying areas of the system that are more defect-prone or have changed frequently, the tool can prioritize or select the most relevant test cases, reducing the overall regression testing effort.

  This directly aligns with Option B, which describes optimization based on past iterations and defect patterns to select the most valuable test cases.

  The other options are incorrect. Clustering test cases alone does not directly reduce regression scope. Bayesian analysis of human interactions is not a standard approach for regression test optimization. A/B testing is used to compare system variants, not to reduce regression test execution.

• Question 113:

  Which of the following statements about explainable AI is correct?

  A. Interpretability refers to how easily users can determine whether the result provided by the AI-based system is correct.
  B. Explainability refers to how easily the algorithms and training data needed to create the model can be determined.
  C. According to The Royal Society, one reason for explainable AI is to increase user confidence in the system.
  D. According to The Royal Society, one reason for explainable AI is to eliminate the need for risk and vulnerability assessments.
  C. According to The Royal Society, one reason for explainable AI is to increase user confidence in the system.

  ---

  Section 2.10 - Explainability and Transparency of the ISTQB CT-AI syllabus describes explainable AI as the ability of a system to provide human-understandable insight into its decisions. The syllabus references The Royal Society's report as a foundational source explaining why explainability is important. Among the stated motivations is the need to increase user trust and confidence in AI systems by making their decisions understandable and justifiable. Therefore, Option C directly reflects the syllabus content.

  Option A is incorrect because interpretability does not refer to determining the correctness of outputs; rather, it refers to understanding how the model arrives at its outputs. Option B incorrectly frames explainability as the ability to investigate algorithms or training data; explainability is about understanding the model's decision-making, not reverse engineering its components. Option D is incorrect because explainability does not eliminate 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 is Option C.

• Question 114:

  Pairwise testing can be used in the context of self-driving cars for controlling an explosion in the number of combinations of parameters. Which ONE of the following options is LEAST likely to be a reason for this incredible growth of parameters?

  A. Different Road Types
  B. Different weather conditions
  C. ML model metrics to evaluate the functional performance
  D. Different features like ADAS, Lane Change Assistance etc.
  C. ML model metrics to evaluate the functional performance

  ---

  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 is least likely to 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, the least likely reason for the incredible growth in the number of parameters is C. ML model metrics to evaluate the functional performance.

• Question 115:

  Which ONE of the following options describes the LEAST LIKELY usage of AI for detection of GUI changes due to changes in test objects?

  A. Using a pixel comparison of the GUI before and after the change to check the differences.
  B. Using computer vision to compare the GUI before and after the test object changes.
  C. Using vision-based detection of GUI layout changes before and after test object changes.
  D. Using an ML-based classifier to flag whether GUI changes should be reviewed by humans.
  A. Using a pixel comparison of the GUI before and after the change to check the differences.

  ---

  Using a pixel-by-pixel comparison of the GUI before and after a change is a traditional image comparison technique and does not involve AI. It performs a direct comparison of pixel values without applying learning, inference, or intelligent interpretation. Therefore, it is the least likely usage of AI for detecting GUI changes.

  Using computer vision techniques to compare GUIs involves AI-based image understanding and is commonly applied to detect visual changes beyond simple pixel differences.

  Using vision-based detection of GUI layout changes leverages AI to analyze structural and spatial relationships within the interface, which is a typical AI-based approach.

  Using an ML-based classifier to determine whether detected GUI changes should be flagged for human review is also a valid AI usage, as it applies learned patterns to support decision-making.

  Therefore, Option A correctly describes the least likely usage of AI for detecting GUI changes.

• Question 116:

  Which of the following statements about the structure and function of neural networks is true?

  A. The bias of a neuron is determined by the activation values of the neurons in the previous layer.
  B. Training a neural network only changes the values of the weights at the connections between neurons.
  C. A single-layer perceptron is NOT a neural network.
  D. The input layer of a deep neural network must have at least as many neurons as its output layer.
  B. Training a neural network only changes the values of the weights at the connections between neurons.

  ---

  Section 1.7 - Neural Networks of the ISTQB CT-AI syllabus explains that neural networks consist of neurons connected by weighted links. During training, learning occurs by adjusting the weights on these connections. This is the essence of gradient descent and backpropagation. Option B correctly states this behavior: only the weights are modified, not the activation functions, the number of neurons, or the architectural structure.

  Option A is incorrect because a neuron's bias is not determined by the activations of neurons in the previous layer; it is an independent trainable parameter added to the weighted sum of inputs. Option C is incorrect because the syllabus states that a single-layer perceptron is a valid type of neural network, although it is limited to linearly separable problems. Option D is incorrect because there is no requirement that the number of input neurons be greater than or equal to the number of output neurons. Input

  neurons correspond to the number of features, while output neurons correspond to tasks or classes.

  Therefore, Option B precisely reflects the syllabus definition of what changes during neural network training.

• Question 117:

  Which of the following is an example of overfitting?

  A. The model is not able to generalize to accommodate new types of data.
  B. The model is too simplistic for the data.
  C. The model is missing relationships between the inputs and outputs.
  D. The model discards data it considers to be noise or outliers.
  A. The model is not able to generalize to accommodate new types of data.

  ---

  The ISTQB CT-AI syllabus defines overfitting as a situation in which an ML model learns the training data too precisely, including noise and irrelevant details, and therefore performs poorly on previously unseen data. A key characteristic of overfitting is the inability to generalize beyond the training dataset.

  Option A directly reflects this definition, as it describes a model that cannot generalize to new data.

  The other options describe different issues. A model that is too simplistic or misses relationships between inputs and outputs indicates underfitting. Discarding noise or outliers is typically part of data cleaning or regularization and does not describe overfitting.

  Therefore, Option A is the correct answer.

• Question 118:

  You are developing a "flower" ML model. Which of the following describes an objection that you can NEGLECT in your risk assessment?

  A. The possible inputs for the "leaf" and "flower" ML models are so different that reuse has few advantages over new development.
  B. The probability of misclassification of the ML model "flower" is higher when it is reused than when it is developed from scratch.
  C. The classification behavior of the "flower" ML model is more difficult to understand when it is reused compared to when it is developed from scratch.
  D. The possible outputs of the "leaf" and "flower" ML models are so different that reuse has few advantages over new development.
  D. The possible outputs of the "leaf" and "flower" ML models are so different that reuse has few advantages over new development.

  ---

  The ISTQB CT-AI syllabus explains that reusing pre-trained models is strongly related to the similarity between the original task and the new task. Section 1.8 - Pre-trained Models and Transfer Learning states that reuse is effective when the new task is similar to the original one, such as adapting a cat classifier to classify dog breeds. The syllabus highlights risks related to differences in input data, data preparation inconsistencies, inherited shortcomings, and explainability issues. These are legitimate

  objections, corresponding to Options A, B, and C, because large differences in input characteristics can undermine transfer learning, the risk of misclassification may increase, and explainability often decreases when reusing pre-trained models.

  However, differences in outputs are not a valid concern in this context. Both the "leaf" and "flower" ML models classify the same plant species, meaning their output classes are identical. The syllabus does not identify output differences as a transfer learning risk when the label space remains the same. Instead, the primary risks relate to inputs, bias inheritance, model transparency, and training differences.

  Therefore, Option D describes an objection that can be safely neglected in the risk assessment.

• Question 119:

  A company is using a spam filter to identify which emails should be marked as spam. Detection rules are created by the filter that cause a message to be classified as spam. An attacker wants all messages internal to the company to be classified as spam. To achieve this, the attacker sends messages with obvious red flags in the body of the email and modifies the "from" field to make it appear that the emails were sent by company members.

  The testers plan to use exploratory data analysis (EDA) to detect the attack and use this information to prevent future adversarial attacks.

  How could EDA be used to detect this attack?

  A. EDA can help detect the outlier emails from the real emails
  B. EDA can detect and remove the false emails
  C. EDA can restrict how many inputs can be provided by unique users
  D. EDA cannot be used to detect the attack
  A. EDA can help detect the outlier emails from the real emails

  ---

  The ISTQB CT-AI syllabus explains that exploratory data analysis (EDA) can be used to examine datasets in order to identify outliers, anomalies, and unusual patterns. In the context of adversarial attacks such as data poisoning, maliciously crafted inputs often differ statistically from legitimate data and may therefore appear as outliers.

  By analyzing distributions, frequencies, and patterns in email metadata and content, EDA can help identify emails that deviate significantly from normal internal communication, indicating a potential attack.

  Therefore, using EDA to detect outlier emails is an appropriate method for identifying this type of adversarial behavior, making Option A the correct answer.

• Question 120:

  Which ONE of the following is the BEST option to optimize regression test selection and prevent the regression suite from growing too large?

  A. Identifying suitable tests by looking at the complexity of the test cases
  B. Using a random subset of tests
  C. Automating test scripts using AI-based test automation tools
  D. Using an AI-based tool to optimize the regression test suite by analyzing past test results
  D. Using an AI-based tool to optimize the regression test suite by analyzing past test results

  ---

  Option A: Identifying suitable tests by looking at the complexity of the test cases While test complexity analysis may help identify important test cases, it does not provide an effective mechanism for continuously optimizing the entire regression suite or preventing uncontrolled growth.

  Option B: Using a random subset of tests Random selection may omit critical test cases and does not provide systematic or risk-based optimization.

  This approach does not ensure adequate regression coverage.

  Option C: Automating test scripts using AI-based test automation tools Automation improves execution efficiency but does not inherently optimize which test cases should be selected or removed from the regression suite.

  Option D: Using an AI-based tool to optimize the regression test suite by analyzing past test results AI-based tools can analyze historical test execution data, defect patterns, and change impact information to prioritize and select the most effective regression tests. This approach helps keep the regression suite both efficient and manageable while maintaining defect detection effectiveness.

  Therefore, Option D is the correct answer.

  Reference

  ISTQB CT-AI Syllabus v1.0, Section 11.4 - AI Support for Test Optimization and Regression Testing