AI0-001 AI Security, Ethics and Governance Practice Test 4 — 15 Questions

Question 1

An AI system in a self-driving car misinterprets a stop sign due to a small sticker placed on it. This is an example of which security vulnerability?

Accepted Answer

Adversarial example attack. The sticker on the stop sign creates a small perturbation that causes the AI model's image classifier to misclassify the sign (e.g., as a speed limit sign). This is the defining characteristic of an adversarial example attack, where crafted input perturbations exploit model vulnerabilities to cause incorrect predictions.

Answer

Supply chain attack

Answer

Model inversion attack

Answer

Data poisoning attack

Question 2

Which TWO of the following are effective techniques for detecting bias in an AI model?

Accepted Answer

Fairness metrics such as equal opportunity difference. Option A, fairness metrics such as equal opportunity difference, is correct because it quantitatively compares true positive rates across protected groups, directly exposing unequal model performance that indicates bias. Option E, disparate impact analysis, is correct because it applies the four-fifths (80%) rule to compare selection or approval rates between groups, a standard legal and statistical method for detecting discriminatory outcomes. Options B, C, and D are not marked correct: feature importance scores only show which inputs influence predictions and do not by themselves reveal bias against a group; a confusion matrix on the entire dataset aggregates all groups and hides per-group disparities unless disaggregated; and cross-validation accuracy measures overall generalization performance, not fairness across subgroups.

Answer

Feature importance scores

Answer

Confusion matrix on the entire dataset

Answer

Cross-validation accuracy

Question 3

Which TWO of the following are common threats to AI model security?

Accepted Answer

Data poisoning. Data poisoning (B) is a core AI-specific threat in which an attacker corrupts the training dataset so the model learns incorrect or malicious behavior, degrading accuracy or implanting backdoors. Adversarial examples (C) are also a fundamental AI model threat, where inputs are deliberately perturbed with small, often imperceptible changes that cause the model to misclassify or produce attacker-chosen outputs. By contrast, SQL injection (A) targets database-driven applications through malicious query strings, not the model itself, and DDoS (D) is an availability attack that floods network or service resources rather than manipulating model behavior. Phishing (E) is a social-engineering attack against users' credentials or trust, not a direct threat to AI model integrity or inference.

Answer

SQL injection

Answer

Distributed denial-of-service (DDoS)

Answer

Phishing attacks

Question 4

A healthcare organization uses an AI model to recommend treatment plans. The model was trained on data from a single hospital, and now treats patients from multiple demographics. Which ethical concern is most critical?

Accepted Answer

Fairness and bias in predictions. The model was trained on data from a single hospital, which likely has a homogeneous demographic profile. When deployed across multiple demographics, the model may produce biased or unfair predictions for underrepresented groups, making fairness and bias the most critical ethical concern. This directly violates the principle of distributive justice in AI ethics.

Answer

Accountability for treatment outcomes

Answer

Lack of transparency in model decisions

Answer

Privacy violations in training data

Question 5

A company implements an AI-based chatbot for customer service. After deployment, customers report that the chatbot sometimes uses offensive language. The development team reviews the training data and finds no explicit offensive content. What is the most likely explanation?

Accepted Answer

The model learned biased language patterns from the training corpus. The chatbot's offensive language likely stems from biased or toxic patterns present in the training corpus, even if no explicit offensive content was flagged. Large language models learn statistical associations from their training data, and if the corpus contains subtle biases, stereotypes, or indirect toxic language, the model can reproduce these patterns in its responses. This is a well-known issue in AI ethics and governance, where models inadvertently amplify societal biases embedded in the data.

Answer

There is a bug in the deployment pipeline

Answer

The model is overfitting to rare examples

Answer

The training data was poisoned by an attacker

Question 6

An organization wants to ensure its AI systems comply with new regulations requiring explanations for automated decisions. Which governance practice is most directly relevant?

Accepted Answer

Deploying explainability tools. Deploying explainability tools (B) is the most directly relevant governance practice because the regulation specifically requires explanations for automated decisions. Explainability tools, such as LIME or SHAP, generate human-interpretable justifications for model outputs, enabling compliance with transparency mandates. This directly addresses the need to understand and communicate why a particular decision was made, unlike other practices that focus on privacy, fairness, or oversight.

Answer

Implementing differential privacy

Answer

Conducting bias audits

Answer

Establishing an AI ethics board

Question 7

A financial institution uses an AI model to approve loans. The model uses features including credit score and ZIP code. During an audit, it is discovered that the model has a high false positive rate for loan default predictions in certain ZIP codes. What should the institution do to address this?

Accepted Answer

Retrain the model with fairness constraints. Retraining the model with fairness constraints directly addresses the root cause of the bias—the model's learned correlations between ZIP code and default risk. Fairness constraints, such as demographic parity or equalized odds, are applied during training to ensure the model's predictions are not systematically skewed against certain groups. This approach preserves the predictive power of legitimate features while mitigating discriminatory outcomes, aligning with AI governance principles.

Answer

Remove the ZIP code feature from the model

Answer

Increase the decision threshold for those ZIP codes

Answer

Discontinue use of the model for those ZIP codes

Question 8

An AI development team is building a system to detect fraudulent transactions. They want to ensure the model complies with regulations requiring that individuals can question automated decisions. Which governance element is most relevant?

Accepted Answer

Right to explanation. The right to explanation is a governance principle that requires automated decision-making systems to provide individuals with meaningful information about how decisions are made. In the context of fraudulent transaction detection, this regulation ensures that a customer can question why a transaction was flagged, and the model must be able to provide an interpretable rationale. This directly aligns with the scenario's requirement for compliance with regulations allowing individuals to question automated decisions.

Answer

Model versioning

Answer

Differential privacy

Answer

Data minimization

Question 9

A security researcher demonstrates that by adding small perturbations to an image of a stop sign, an autonomous vehicle's AI misclassifies it as a speed limit sign. This is an example of which type of attack?

Accepted Answer

Adversarial example attack. This is an adversarial example attack because the researcher adds imperceptible perturbations to the input image (the stop sign) to cause the AI model to output an incorrect classification (speed limit sign). Adversarial examples exploit the model's sensitivity to small, crafted changes in input data, leading to misclassification without altering the underlying task or training data.

Answer

Data poisoning attack

Answer

Model extraction attack

Answer

Membership inference attack

Question 10

Which TWO of the following are common methods for mitigating bias in AI models?

Accepted Answer

Reweighting training samples based on sensitive attributes. Option B (Reweighting training samples based on sensitive attributes) is correct because it is a standard pre-processing bias-mitigation technique: by assigning higher weights to underrepresented or historically disadvantaged groups, the model's loss function is adjusted so those samples contribute more to the learned parameters, reducing disparate impact across sensitive attributes. Option D (Adding fairness constraints during training) is correct because it is a standard in-processing technique: fairness metrics such as demographic parity, equalized odds, or disparate impact are encoded as constraints or penalty terms in the objective function, forcing the optimizer to trade off accuracy against a quantified fairness criterion. The other options do not belong: A (adversarial training) is primarily used to improve robustness against adversarial examples, not to mitigate bias; C (L1 regularization) induces sparsity in weights for feature selection and generalization, not fairness; and E (k-fold cross-validation) is a model-evaluation/resampling method for estimating generalization performance, not a bias-mitigation method.

Answer

Using adversarial training

Answer

Applying L1 regularization

Answer

Performing k-fold cross-validation

Question 11

Which THREE of the following are key principles of AI ethics as defined by major frameworks?

Accepted Answer

Transparency. Transparency (A) is a core AI-ethics principle because major frameworks require that AI systems' capabilities, limitations, data use, and decision logic be disclosed and explainable to affected stakeholders. Accountability (C) is likewise fundamental, as frameworks such as the OECD AI Principles and UNESCO Recommendation demand that responsibility for AI outcomes be clearly assigned to identifiable humans or organizations, with mechanisms for redress. Fairness (E) is a third key principle, requiring that AI systems avoid unjust bias and discrimination and treat individuals and groups equitably across the lifecycle. By contrast, scalability (B) is an engineering and performance concern about handling growing workloads, and latency (D) is a technical metric of response delay; neither is an ethical principle in AI frameworks.

Answer

Scalability

Answer

Latency

Question 12

A bank uses an AI model to approve loans. During an audit, it is found that the model denies loans at a higher rate for a certain ethnic group. Which governance principle is primarily violated?

Accepted Answer

Fairness. The model's disparate impact on a specific ethnic group directly violates the principle of Fairness, which requires that AI systems do not discriminate based on protected attributes such as race, ethnicity, or gender. In lending, fairness is often assessed using metrics like demographic parity or equal opportunity, and a higher denial rate for one group indicates a lack of algorithmic fairness.

Answer

Accountability

Answer

Transparency

Answer

Privacy

Question 13

A company deployed an AI chatbot that started generating offensive responses after a data update. The security team needs to quickly mitigate the issue. What should they do first?

Accepted Answer

Disable the chatbot and investigate. The first priority when an AI chatbot generates offensive responses is to stop the harm immediately. Disabling the chatbot (Option B) halts all user interactions, preventing further offensive outputs while the security team investigates the root cause. This aligns with the principle of containment before remediation in incident response.

Answer

Delete the training data

Answer

Roll back to previous model version

Answer

Add a content filter

Question 14

An organization wants to implement an AI ethics board. Which composition best ensures independence and expertise?

Accepted Answer

Mix of internal stakeholders and external ethicists. An AI ethics board must combine internal stakeholders (who understand organizational context, data flows, and operational constraints) with external ethicists (who provide independent, unbiased perspectives and specialized knowledge of ethical frameworks like IEEE Ethically Aligned Design or the EU AI Act). This composition ensures the board can evaluate AI systems for bias, fairness, and transparency without being dominated by business or technical interests, which is critical for maintaining trust and regulatory compliance.

Answer

All members from the legal department

Answer

IT department head and data scientists

Answer

Only senior executives from the company

Question 15

A healthcare AI system misdiagnosed patients due to adversarial inputs. What security measure should be prioritized?

Accepted Answer

Implement adversarial training. (Implement adversarial training) is correct because adversarial training makes the model robust to input manipulation. Option A (Encrypt all patient data) protects data privacy but not model integrity. Option B (Use stronger authentication) is for access control. Option C (Regular software updates) is general maintenance and does not specifically address adversarial inputs.

Answer

Encrypt all patient data

Answer

Use stronger authentication

Answer

Regular software updates