AI0-001 AI Security, Ethics and Governance Practice Test 6 — 15 Questions

Question 1

What is the primary function of an AI ethics board within an organization?

Accepted Answer

Reviewing AI projects for ethical compliance. The primary function of an AI ethics board is to review AI projects for ethical compliance, ensuring that the organization's AI systems adhere to established ethical principles, legal standards, and governance frameworks. This board typically assesses risks related to bias, fairness, transparency, and accountability before deployment, rather than engaging in technical development or operational tasks.

Answer

Developing algorithms

Answer

Managing cloud infrastructure

Answer

Marketing AI products

Question 2

Which THREE are key principles of trustworthy AI according to the OECD?

Accepted Answer

Robustness. The OECD's Recommendation on Artificial Intelligence defines trustworthy AI around principles including robustness, transparency, and accountability, so options B, C, and E are correct. Robustness (B) is required because AI systems must function reliably, safely, and securely throughout their lifecycle, including resilience to errors and adversarial manipulation. Transparency (C) is a core principle because AI systems should be understandable and disclose meaningful information about their capabilities, limitations, and decision-making so stakeholders can assess them. Accountability (E) is also essential because organizations and individuals deploying or operating AI must remain answerable for the system's outcomes and provide redress where appropriate. Profitability (A) and scalability (D) are business or engineering goals, not OECD trustworthy-AI principles, so they do not belong.

Answer

Profitability

Answer

Scalability

Question 3

A large hospital system deploys an AI triage system for emergency rooms. The system uses patient vitals and symptoms to recommend treatment priority. Six months after deployment, complaints arise that the system frequently underestimates the severity of symptoms for patients from certain ethnic backgrounds. A data scientist runs a bias audit and finds that the model's false negative rate is 20% higher for the minority group. The hospital's AI governance board requires immediate corrective action. The data science team has limited resources and cannot retrain the entire model from scratch. They have access to the training data, which is imbalanced. The model is a gradient boosted tree. Which course of action best addresses the bias while minimizing operational impact?

Accepted Answer

Post-process the model's predictions by adjusting thresholds for the minority group. Post-processing by adjusting decision thresholds for the minority group directly compensates for the higher false negative rate without requiring retraining. Since the team has limited resources and cannot retrain the entire gradient boosted tree model, this approach minimizes operational impact while addressing the bias. The threshold adjustment effectively lowers the probability cutoff for the minority group, making the model more sensitive to their symptoms and reducing underestimation of severity.

Answer

Rebalance the training data using SMOTE and retrain the model

Answer

Use adversarial debiasing during training to remove protected attribute correlations

Answer

Replace the model with a simpler logistic regression model to improve interpretability

Question 4

A security analyst is reviewing logs from an AI-powered recommendation system and notices an unusually high number of requests for products from a specific vendor. The analyst suspects data poisoning. Which mitigation strategy should be implemented first?

Accepted Answer

Implement input validation and sanitization for training data. Input validation and sanitization directly prevent malicious or anomalous data from entering the training pipeline, which is the root cause of data poisoning. In an AI-powered recommendation system, poisoned training data can cause the model to learn biased associations, such as favoring a specific vendor. By validating and sanitizing inputs before they are used for training, the attack vector is blocked at the earliest stage, making it the most effective first mitigation step.

Answer

Encrypt all training data at rest

Answer

Deploy an anomaly detection system on model outputs

Answer

Retrain the model with a smaller, curated dataset

Question 5

A healthcare startup deploys an AI model to predict patient readmission rates. An internal audit reveals that the model consistently underestimates readmission risk for non-native English speakers. According to AI ethics principles, what is the most appropriate course of action?

Accepted Answer

Retrain the model with a more representative dataset that includes diverse language backgrounds. It directly addresses the root cause of the bias: the training data lacks sufficient representation from non-native English speakers, leading to systematic underestimation of readmission risk for that group. Retraining with a more representative dataset aligns with the AI ethics principle of fairness by ensuring the model learns patterns across all demographic groups equally, rather than masking the issue with disclaimers or manipulating sample sizes.

Answer

Add a confidence score disclaimer to model outputs

Answer

Reduce the sample size of non-native English speakers to balance the dataset

Answer

Continue using the model as is, since overall accuracy is acceptable

Question 6

During a penetration test, a security engineer discovers that an AI-powered chatbot can be tricked into revealing sensitive customer data by using specially crafted prompts. What type of attack is this, and what is the best mitigation?

Accepted Answer

Prompt injection attack; implement input validation and context sanitization. This is a prompt injection attack, where an attacker crafts inputs that cause the AI model to override its original instructions or constraints, leading to unintended behavior such as revealing sensitive data. The best mitigation is input validation and context sanitization, which filters or neutralizes malicious prompt content before it reaches the model, preventing the injection from succeeding.

Answer

Model inversion attack; apply differential privacy during training

Answer

Data poisoning attack; implement strict access controls

Answer

Membership inference attack; add noise to model outputs

Question 7

A financial institution uses an AI model to approve small business loans. The model has a high approval rate for women-owned businesses but low for minority-owned businesses. The compliance officer is concerned about disparate impact. Which governance process should be implemented first?

Accepted Answer

Conduct a bias audit and fairness assessment using relevant metrics. A bias audit and fairness assessment should be conducted first to quantify the disparate impact and identify root causes. Option A is wrong because simply removing sensitive features does not guarantee fairness and may be insufficient or illegal. Option C is wrong because publishing decision-making criteria without first addressing bias could expose the institution to liability and undermine trust. Option D is wrong because adjusting the approval threshold without thorough analysis can be arbitrary, may not address underlying bias, and could lead to reverse discrimination or mask systemic issues.

Answer

Remove gender and ethnicity features from the model

Answer

Publish the model's decision-making criteria to the public

Answer

Immediately adjust the approval threshold to equalize rates

Question 8

An organization deploys an AI system that processes personal data of EU citizens. Which regulatory framework imposes strict requirements on automated decision-making and profiling?

Accepted Answer

General Data Protection Regulation (GDPR). The General Data Protection Regulation (GDPR) is the correct regulatory framework because it specifically governs the processing of personal data of EU citizens and imposes strict requirements on automated decision-making and profiling under Article 22. This article grants individuals the right not to be subject to a decision based solely on automated processing, including profiling, which produces legal effects or similarly significant effects. The GDPR also mandates data protection impact assessments and transparency obligations for such AI-driven processing.

Answer

Payment Card Industry Data Security Standard (PCI DSS)

Answer

Health Insurance Portability and Accountability Act (HIPAA)

Answer

Sarbanes-Oxley Act (SOX)

Question 9

Which TWO of the following are common techniques to improve the transparency and interpretability of an AI model?

Accepted Answer

Generate SHAP (SHapley Additive exPlanations) values. Option A is correct because SHAP (SHapley Additive exPlanations) values, grounded in cooperative game theory, assign each feature a quantitative contribution to a prediction, providing both global and local interpretability for any model. Option E is correct because LIME (Local Interpretable Model-agnostic Explanations) approximates a complex model's behavior around a single prediction with a simple, interpretable surrogate model, exposing which features drove that decision. Both techniques are model-agnostic post-hoc explanation methods specifically designed to make AI outputs transparent and interpretable. Option B is not a transparency technique: differential privacy adds calibrated noise to protect individual records, trading accuracy for privacy rather than explaining model behavior. Option C is not inherently an interpretability technique; random forests are ensembles whose many trees are typically less transparent than a single decision tree. Option D is incorrect because increasing complexity with deep neural networks generally reduces interpretability rather than improving it.

Answer

Use differential privacy to add noise to training data

Answer

Implement a random forest algorithm

Answer

Use deep neural networks to increase model complexity

Question 10

Which TWO of the following are effective defenses against adversarial examples in AI systems?

Accepted Answer

Train the model with adversarial examples (adversarial training). Adversarial training (option A) is a correct defense because it augments the training set with adversarial examples generated by attacks such as FGSM or PGD, so the model learns to classify perturbed inputs correctly and its decision boundary becomes more robust. Input sanitization and feature squeezing (option D) are also correct because they preprocess inputs to remove or reduce the adversarial perturbation — for example, by quantizing pixel values, spatial smoothing, or reducing color bit depth — which shrinks the attacker's effective search space and can neutralize small perturbations. Option B is not marked correct because model ensembles with majority voting can sometimes improve robustness but are not a reliable standalone defense; attackers can craft transferable or ensemble-aware adversarial examples that fool all members. Option C is wrong because increasing sensitivity to input changes is the opposite of what is wanted — it makes the model easier to fool with tiny perturbations. Option E is wrong because pruning reduces model complexity for efficiency and may slightly alter robustness, but it is not an established defense against adversarial examples and can even degrade robustness.

Answer

Use an ensemble of models and majority voting

Answer

Increase the model's sensitivity to input changes

Answer

Reduce model complexity through pruning

Question 11

Which THREE of the following are key principles of trustworthy AI as defined by major regulatory bodies?

Accepted Answer

Fairness and non-discrimination. Fairness and non-discrimination (A) is a core principle because trustworthy AI frameworks such as the EU AI Act and OECD AI Principles require systems to avoid biased outcomes and unjust discrimination across protected groups. Transparency and explainability (B) is also correct, as these bodies mandate that AI decisions be understandable and that stakeholders can access meaningful information about how systems operate. Accountability (E) is correct because trustworthy AI requires clear responsibility and redress mechanisms, ensuring that developers and deployers can be held answerable for system outcomes. Maximum profitability (C) is not a trustworthiness principle; it is a business objective and is not part of regulatory AI ethics definitions. Proprietary secrecy (D) is also not a principle, since trustworthiness frameworks emphasize disclosure, auditability, and transparency rather than concealment.

Answer

Maximum profitability

Answer

Proprietary secrecy

Question 12

A large e-commerce company uses a recommendation engine trained on millions of user interactions. Recently, the marketing team noticed a sharp increase in click-through rates for a particular product category. Upon investigation, an engineer found that a competitor had injected fake user profiles that consistently clicked on their products, skewing the training data. The company needs to remediate the attack and prevent future occurrences. The team has limited time and budget. Which course of action should the company take first?

Accepted Answer

Identify and remove the fake user profiles from the training dataset, then retrain the model. The immediate priority is to remove the poisoned data from the training set and retrain the model, as the fake profiles are actively skewing predictions and causing incorrect click-through rate spikes. This direct remediation addresses the root cause with minimal time and budget, aligning with the team's constraints. Without cleaning the data, any further training or defensive measures would still operate on corrupted inputs.

Answer

Implement adversarial training to make the model robust to future poisoning attempts

Answer

Decrease the frequency of model retraining to limit exposure to new data

Answer

Add differential privacy noise to the training data to mask the injected profiles

Question 13

A hospital deploys an AI diagnostic assistant that analyzes medical images. The system has been in use for six months, and radiologists have reported that the AI is increasingly confident in its predictions, but sometimes misses rare conditions. The AI ethics board is concerned about overreliance and potential harm from false negatives. They want to implement a governance framework that ensures appropriate human oversight. The hospital has a limited IT budget. What is the best approach?

Accepted Answer

Implement a human-in-the-loop process where the AI flags low-confidence or rare condition predictions for mandatory radiologist review. A human-in-the-loop process that triggers mandatory radiologist review only for low-confidence or rare-condition predictions directly addresses the risk of overreliance and false negatives without overwhelming the limited IT budget. This targeted oversight ensures that the AI's increasing confidence does not lead to missed rare conditions, while still allowing routine high-confidence predictions to proceed efficiently. The approach balances safety and resource constraints by focusing human attention where the AI is most likely to err.

Answer

Add a warning to the AI interface that says 'This tool may miss rare conditions'

Answer

Require all AI predictions to be reviewed by a radiologist before final diagnosis

Answer

Increase the AI's false positive threshold to reduce missed cases

Question 14

A social media company uses an AI content moderation system to filter hate speech. The system uses a natural language processing model trained on user reports. Recently, the model's false positive rate has increased, blocking legitimate posts. An internal audit reveals that a coordinated group of users has been falsely reporting harmless posts, causing the model to learn incorrect patterns. The company needs to address the attack and restore accuracy. The engineering team can modify the training pipeline. What is the most effective first step?

Accepted Answer

Redesign the training pipeline to incorporate a reputation system for reporting users. The root cause is a coordinated attack where malicious users exploit the reporting mechanism to poison the training data. Incorporating a reputation system into the training pipeline allows the model to weigh or filter user reports based on the trustworthiness of the reporting user, directly mitigating the impact of false reports without discarding legitimate feedback. This addresses the adversarial behavior at the source, restoring accuracy by ensuring the model learns from reliable signals.

Answer

Increase the weight of non-reported posts to counteract the reported posts' influence

Answer

Apply adversarial training to make the model robust to crafted inputs

Answer

Retrain the model on a dataset that excludes all user-reported posts

Question 15

A national security agency uses AI to analyze surveillance data for threat detection. The system is deployed in a high-stakes environment where false negatives could lead to missed threats, and false positives waste analyst time. Recently, a known hacker group attempted to evade detection by subtly modifying their communication patterns over time, a form of adversarial evasion. The agency wants to harden the system while maintaining performance. The system uses a deep neural network. Which mitigation strategy is most appropriate?

Accepted Answer

Perform adversarial training using the hacker group's known evasion patterns. Adversarial training is the most appropriate mitigation because it directly incorporates known evasion patterns into the training process, making the deep neural network robust to the hacker group's subtle modifications. By retraining the model on adversarial examples, the decision boundary is hardened against these specific attacks without sacrificing overall detection performance. This approach is a standard defense in high-stakes security AI, balancing false positive and false negative rates while countering adversarial evasion.

Answer

Switch to an unsupervised learning approach to detect anomalies

Answer

Simplify the model to a logistic regression to reduce the attack surface

Answer

Add random noise to all input data to confuse evasion attempts