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

ISQI ISQI-CT-AI Online Questions & Answers

• Question 91:

  "AllerEgo" is a product that uses self-learning to predict the behavior of a pilot under combat situations for a variety of terrains and enemy aircraft formations. After training, the model was exposed to real-world data, and the model was found to be performing poorly. A large number of data quality tests had been performed on the data to bring it into a shape fit for training and testing. Which ONE of the following options is least likely to describe the possible reason for the drop in performance, especially when considering the self-learning nature of the AI system?

  A. The difficulty of defining criteria for improvement before the model can be accepted.
  B. The fast pace of change did not allow sufficient time for testing.
  C. The unknown nature and insufficient specification of the operating environment might have caused the poor performance.
  D. There was an algorithmic bias in the AI system.
  A. The difficulty of defining criteria for improvement before the model can be accepted.

  ---

  The ISTQB CT-AI syllabus describes several challenges that can negatively affect the performance of self-learning AI systems in real-world operation. These include insufficient testing time when systems evolve rapidly, poorly specified or unknown operating environments, and algorithmic bias, all of which can lead to degraded performance when the system encounters new or changing conditions.

  Options B, C, and D are therefore plausible reasons for the observed performance decline. A fast pace of change can limit adequate testing, an insufficiently specified operating environment can hinder effective adaptation, and algorithmic bias can cause systematic performance issues across scenarios.

  Option A, however, relates to difficulties in defining acceptance or improvement criteria before deployment. While this is a recognized challenge during evaluation and acceptance of AI systems, it does not directly cause a performance drop when the system is exposed to real-world data. It affects decision-making about acceptance rather than the operational behavior of the self-learning system.

  Therefore, Option A is the least likely reason for the observed decrease in performance.

• Question 92:

  Data used for an object detection ML system was found to have been labeled incorrectly in many cases. Which ONE of the following options is MOST LIKELY the reason for this problem?

  A. Security issues
  B. Accuracy issues
  C. Privacy issues
  D. Bias issues
  B. Accuracy issues

  ---

  The ISTQB CT-AI syllabus identifies accuracy of data and labels as a key data quality aspect. Incorrectly labeled data directly indicates a problem with labeling accuracy, as the labels do not correctly represent the objects in the data. Such inaccuracies lead to misleading training signals and degrade the model's learning and predictive performance.

  Security issues relate to unauthorized access or data breaches, not labeling correctness. Privacy issues concern the handling of personal or sensitive data and are unrelated to labeling errors. Bias issues involve systematic skew or unfair representation in the data, rather than labels being factually wrong.

  Therefore, accuracy issues (Option B) are the most likely reason for the incorrectly labeled data.

• Question 93:

  Which of the following characteristics of AI-based systems makes it more difficult to ensure they are safe?

  A. Simplicity
  B. Sustainability
  C. Non-determinism
  D. Robustness
  C. Non-determinism

  ---

  The ISTQB CT-AI syllabus states that non-determinism is one of the key characteristics that makes ensuring safety in AI-based systems more difficult. Non-deterministic behavior means that the same input may lead to different outputs, which complicates predictability, verification, and validation.

  The syllabus explicitly lists the following characteristics as challenges to safety assurance in AI-based systems: complexity, non-determinism, probabilistic behavior, self-learning, lack of transparency, interpretability and explainability, and lack of robustness.

  Simplicity and sustainability do not inherently introduce safety risks. Robustness is a desired quality attribute; rather, a lack of robustness increases safety risk.

  Therefore, Non-determinism (Option C) is the correct answer.

• Question 94:

  Which of the following is correct regarding the layers of a deep neural network?

  A. There is only an input and output layer.
  B. There is at least one internal hidden layer.
  C. There must be a minimum of five total layers to be considered deep.
  D. The output layer is not connected with the other layers to maintain integrity.
  B. There is at least one internal hidden layer.

  ---

  The ISTQB CT-AI syllabus clearly explains the structure of a deep neural network (DNN). A deep neural network consists of three types of layers: an input layer that receives the input data, one or more hidden layers composed of artificial neurons (also referred to as nodes), and an output layer that produces the final result. The defining characteristic of a deep neural network is the presence of at least one hidden layer between the input and output layers.

  This directly supports Option B, which correctly states that a deep neural network has at least one internal hidden layer.

  The other options are incorrect. A network with only input and output layers would not be considered deep. There is no minimum requirement of five total layers for a network to be classified as deep. The output layer must be connected to the preceding layers in order to receive processed information; it is not isolated to maintain integrity.

  Thus, Option B is the correct statement.

• Question 95:

  You have been developing test automation for an e-commerce system. One of the problems you are seeing is that object recognition in the GUI is having frequent failures. You have determined this is because the developers are changing the identifiers when they make code updates. How could AI help make the automation more reliable?

  A. It could identify the objects in multiple ways and then determine the most commonly used and stable identification for each object.
  B. It could modify the automation code to ignore unrecognizable objects to avoid failures.
  C. It could dynamically name the objects, altering the source code, so the object names will match the object names used in the automation.
  D. It could generate a model that will anticipate developer changes and pre-alter the test automation code accordingly.
  A. It could identify the objects in multiple ways and then determine the most commonly used and stable identification for each object.

  ---

  The ISTQB CT-AI syllabus discusses the use of AI-based tools to reduce the brittleness of GUI-based test automation. Frequent failures often occur when identifiers such as IDs, XPaths, or class names change between releases.

  The syllabus states that:

  "AI can be used to reduce the brittleness of this approach by employing AI-based tools to identify the correct objects using various criteria (e.g., XPath, label, id, class, X/Y coordinates), and to choose the historically most stable identification criteria."

  This directly aligns with Option A, which describes identifying GUI objects using multiple attributes and selecting the most stable and reliable identifiers over time.

  The other options are incorrect because ignoring objects reduces test value, modifying source code is not a tester responsibility, and predicting developer changes is unrealistic and unsupported by the syllabus.

  Therefore, Option A is the correct and syllabus-aligned answer.

• Question 96:

  Which of the following are valid uses of AI for supporting software testing? (Choose three) A. Regression test selection optimization

  B. Defect prediction

  C. GUI object recognition

  D. Static code compilation

  Correct Answer. ABC
  ABC

  ---

• Question 97:

  Which challenge to testing self-learning systems puts you at risk of a data attack?

  A. Inadequate specification of the operating environment
  B. Complex test environment
  C. Insufficient testing time
  D. Unexpected changes
  D. Unexpected changes

  ---

  The ISTQB CT-AI syllabus describes that self-learning systems continuously adjust their behavior during operation as new data arrives. Section 4.1 - Challenges of Testing AI-Based Systems highlights that such systems are vulnerable to data attacks, particularly through adversarial inputs, data poisoning, or malicious drift. The risk arises because unexpected changes in the input data distribution may alter the learned model in harmful ways. Option D - Unexpected changes corresponds directly to this

  syllabus-defined risk.

  Option A refers to system specification issues but does not relate to data attacks. Option B discusses environmental complexity, which makes testing more difficult but is not directly tied to adversarial threats. Option C (insufficient testing time) affects overall quality but does not specifically increase vulnerability to malicious data manipulation.

  Unexpected changes---including data drift, poisoned samples, or maliciously constructed training data---pose the greatest risk. When a self-learning system adapts to altered data patterns, it may unknowingly learn incorrect associations, leading to model degradation or manipulation. Therefore, Option D correctly identifies the challenge that increases exposure to data attacks.

• Question 98:

  Which ONE of the following tests is LEAST likely to be performed during the ML model testing phase?

  A. Testing the accuracy of the classification model.
  B. Testing the API of the service powered by the ML model.
  C. Testing the speed of the training of the model.
  D. Testing the speed of the prediction by the model.
  C. Testing the speed of the training of the model.

  ---

  The question asks which test is least likely to be performed during the ML model testing phase. Let's consider each option:

  Testing the accuracy of the classification model (A): Accuracy testing is a fundamental part of the ML model testing phase. It ensures that the model correctly classifies the data as intended and meets the required performance metrics.

  Testing the API of the service powered by the ML model (B): Testing the API is crucial, especially if the ML model is deployed as part of a service. This ensures that the service integrates well with other systems and that the API performs as expected.

  Testing the speed of the training of the model (C): This is least likely to be part of the ML model testing phase. The speed of training is more relevant during the development phase when optimizing and tuning the model. During testing, the focus is more on the model's performance and behavior rather than how quickly it was trained.

  Testing the speed of the prediction by the model (D): Testing the speed of prediction is important to ensure that the model meets performance requirements in a production environment, especially for real- time applications.

  ISTQB CT-AI Syllabus Section 3.2 on ML Workflow and Section 5 on ML Functional Performance Metrics discuss the focus of testing during the model testing phase, which includes accuracy and prediction speed but not the training speed.

• Question 99:

  A system is to be developed to detect lung cancer using X-ray images. Which statement BEST describes the difference between a conventional system and an AI system with supervised machine learning?

  A. The results of analyzing an X-ray for lung cancer using an AI system are more understandable than with a conventional system.
  B. The X-ray images that an AI system can analyze must be structurally different from X-ray images used in a conventional system.
  C. An AI system independently determines patterns in X-rays during training; a conventional system requires a human to program in those patterns.
  D. The implementation of an AI system consists mainly of training data, whereas that of a conventional system consists of branches and loops.
  C. An AI system independently determines patterns in X-rays during training; a conventional system requires a human to program in those patterns.

  ---

  The syllabus explains the fundamental distinction between conventional systems and AI-based systems using supervised machine learning in Section 1.3 - AI-Based and Conventional Systems. A conventional system relies on human- programmed logic---such as branches, conditions, and explicit rules---to interpret input data. The system behaves exactly as specified by its developers.

  In contrast, AI systems using supervised learning automatically learn patterns from labeled data. The syllabus states that "patterns in data are used by the system to determine how it should react in the future... The AI determines on its own what patterns or features in the data can be used." This aligns directly with Option C: an AI system identifies relevant diagnostic patterns in X-ray images during training, whereas a conventional system requires human experts to explicitly program those patterns.

  Option A is incorrect because AI outputs are typically less explainable, not more. Option B is incorrect because both systems can use the same X-ray images; machine learning does not require structurally different images. Option D is oversimplified and not fully accurate; while training data is central to machine learning, AI systems also include architecture, algorithms, and preprocessing---not just data.

  Thus, Option C is the correct and syllabus-aligned answer.

• Question 100:

  Which ONE of the following hardware is MOST suitable for implementing AI when using machine learning (ML)?

  A. 64-bit CPUs
  B. Hardware supporting fast matrix multiplication
  C. High-powered CPUs
  D. Hardware supporting high-precision floating-point operations
  B. Hardware supporting fast matrix multiplication

  ---

  The ISTQB CT-AI syllabus explains that many machine learning algorithms---especially neural networks and deep learning---are heavily based on matrix and vector operations. As a result, hardware that supports fast matrix multiplication is particularly well suited for AI and ML workloads.

  Option B is correct because specialized hardware such as GPUs and tensor processing units (TPUs) is designed to perform large-scale parallel matrix operations efficiently, which significantly accelerates training and inference of ML models.

  Option A is incorrect because 64-bit CPUs, while important for addressing large memory spaces, are not specifically optimized for the parallel numerical computations required by ML algorithms. Option C is incorrect because high-powered CPUs are general-purpose and typically less efficient than specialized accelerators for large-scale matrix operations. Option D is incorrect because although high-precision floating-point operations are relevant in some domains, ML workloads usually benefit more from

  speed and parallelism than from very high numerical precision.

  Therefore, hardware supporting fast matrix multiplication (Option B) is the most suitable choice for implementing AI systems based on machine learning.