AAISM Practice Exam 2 — 20 Questions

Question 1

An attacker is performing a 'Model Extraction' attack. What is the most likely goal of the attacker?

Accepted Answer

To steal the intellectual property of the model architecture.. Model extraction (or theft) aims to recreate the functionality or proprietary logic of a model by querying it and training a substitute model.

Answer

To gain access to the raw training database.

Answer

To cause the model to crash.

Answer

To inject malicious weights into the model.

Question 2

A researcher is using 'Adversarial Training' to defend against evasion. How exactly does this work?

Accepted Answer

It trains the model on adversarial examples alongside clean data.. Adversarial training includes adversarial examples in the training set, allowing the model to learn to classify them correctly.

Answer

It uses a secondary model to detect malicious input.

Answer

It restricts input to a whitelist of authorized users.

Answer

It adds noise to the weights of the model.

Question 3

Which TWO security controls are recommended for protecting 'Training Data'?

Accepted Answer

Encryption at rest for all dataset storage.. Training data should be protected using access controls and encryption at rest to prevent unauthorized access.

Answer

Publicly hosting the data on GitHub for reproducibility.

Answer

Storing all passwords in the training data.

Answer

Using only high-resolution images.

Question 4

Which THREE steps are needed for 'AI Risk Assessment'?

Accepted Answer

Perform a threat modeling exercise.. Assessment requires identifying the AI components, evaluating threats, and determining the business impact.

Answer

Publish the risk assessment on the public internet.

Answer

Train a new model to verify the findings.

Question 5

Which team should lead the definition of 'AI Acceptable Use' policies?

Accepted Answer

A cross-functional committee including legal, privacy, and security.. Cross-functional teams including legal, privacy, security, and business stakeholders ensure the policy is balanced and enforceable.

Answer

The marketing department.

Answer

The software engineering team only.

Answer

The IT helpdesk team.

Question 6

What is the primary role of 'Model Versioning' in AI governance?

Accepted Answer

To ensure reproducibility and enable rollback of problematic versions.. Versioning ensures that changes to the model can be tracked, reverted, and audited, which is vital for reproducibility and risk control.

Answer

To automate user login.

Answer

To maximize server storage usage.

Answer

To hide model architecture from hackers.

Question 7

Which THREE technical controls are recommended to secure an AI model's API endpoint?

Accepted Answer

Enforcing strict schema validation on all inputs.. Securing AI APIs requires defense-in-depth including rate limiting, authentication, and input sanitization.

Answer

Encrypting the model weights at rest in the cloud.

Answer

Removing all logging to prevent log injection.

Question 8

What is the most effective control to prevent 'Model Scraping' from an exposed AI prediction API?

Accepted Answer

Implement tiered access and rate limiting.. Rate limiting and request authentication are the standard controls to prevent automated extraction of model knowledge.

Answer

Require users to sign a Terms of Service agreement.

Answer

Increase the complexity of the model.

Answer

Use an obfuscated model file name.

Question 9

You are assessing the risk of 'Data Poisoning'. Which stage of the machine learning lifecycle is most vulnerable to this attack?

Accepted Answer

Training data collection and ingestion.. Data poisoning occurs during the training data ingestion phase, where malicious samples are injected into the training set.

Answer

The model design and architecture selection.

Answer

Model monitoring and logging.

Answer

Inference and deployment.

Question 10

What is the goal of an 'AI Security Awareness Program'?

Accepted Answer

To educate employees on AI security risks and safe usage.. To ensure all staff understand the risks of AI, including prompt injection, data leakage, and ethical pitfalls.

Answer

To write Python code for everyone.

Answer

To mandate AI usage in all tasks.

Answer

To replace human workers.

Question 11

Which TWO factors are critical when assessing the risk of a new Generative AI use case?

Accepted Answer

The potential business impact if the system fails.. Business impact and data sensitivity are the foundational elements for risk assessment in AI.

Answer

The aesthetic of the user interface.

Answer

The office location of the developers.

Answer

The programming language used.

Question 12

Which TWO activities ensure 'AI Safety' in development?

Accepted Answer

Adversarial testing (red teaming).. Adversarial testing and rigorous documentation are key safety practices.

Answer

Using unmonitored cloud servers.

Answer

Increasing the amount of public data used.

Answer

Removing all encryption.

Question 13

Which THREE documents are vital for an AI audit trail?

Accepted Answer

Model validation and testing reports.. Model version, training set, and validation report are the three pillars of a reconstructible audit trail.

Answer

The office lease agreement.

Answer

A copy of the employee handbook.

Question 14

When using a 'Managed AI API' service, what is the best practice for handling API keys?

Accepted Answer

Store keys in a secure Secrets Manager. API keys should never be hardcoded; they should be stored in secrets managers like AWS Secrets Manager or Azure Key Vault.

Answer

Hardcode keys in the application source code

Answer

Email keys to team members for easy access

Answer

Embed keys in the public Git repository

Question 15

Which tool is best for managing 'Secrets' (like database passwords or API keys) used by your AI training pipeline?

Accepted Answer

HashiCorp Vault. Secrets management services (AWS Secrets Manager, HashiCorp Vault) are the secure way to manage credentials.

Answer

Hardcoded variables in the training script

Answer

A public Github repository

Answer

An Excel spreadsheet on a shared drive

Question 16

Which TWO of the following are primary risks associated with 'membership inference attacks' against an AI model?

Accepted Answer

Exposure of sensitive information about training data subjects.. Membership inference attacks aim to determine if a specific data point was used in the training set, risking privacy leakage.

Answer

Unauthorized modification of model weights.

Answer

Unauthorized access to the model training algorithm.

Answer

Complete system shutdown via resource exhaustion.

Question 17

What is the purpose of 'AI Model Inventory'?

Accepted Answer

To provide a central list of all AI assets for risk oversight.. An inventory tracks all models in production to ensure they are managed, monitored, and reviewed according to organizational policy.

Answer

To increase the speed of the training pipeline.

Answer

To reduce the number of GPUs used.

Answer

To automatically retrain all models.

Question 18

Which TWO components are essential for a robust AI Governance framework?

Accepted Answer

Defined roles and accountability structures.. Policies and clearly defined roles are the foundation of any governance system.

Answer

The company party schedule.

Answer

A list of all employee names.

Answer

The best-selling AI books.

Question 19

Which THREE items should be included in an 'AI Inventory'?

Accepted Answer

Unique model identifier and version.. Model version, owner, and risk rating are the core pieces of information needed to manage an AI portfolio.

Answer

The model's favorite color.

Answer

The developer's favorite food.

Question 20

An organization is using an LLM-based agent. What is the primary risk associated with 'indirect prompt injection' in this environment?

Accepted Answer

External data retrieved by the agent contains instructions that override system prompts.. Indirect prompt injection occurs when malicious data is embedded in a retrieved document that instructs the LLM to perform unintended actions.

Answer

The model produces hallucinatory facts.

Answer

The API key for the LLM is exposed in the code.

Answer

The training data includes PII of users.