An auditor is reviewing a production computer-vision system and must assess whether the team has implemented adequate monitoring for concept drift. Which TWO indicators should the auditor expect to be tracked on an ongoing basis? (Choose two.)
An auditor is evaluating bias in a model deployed on AWS SageMaker. Which tool should be used to generate a report on pre-training and post-training bias metrics?
When auditing an Azure Machine Learning pipeline, which functionality within 'Responsible AI dashboard' is required to perform counterfactual analysis on model predictions?
An auditor is evaluating an AI system's robustness against adversarial attacks. Which technique involves perturbing input data to see if the model output changes significantly?
You are auditing a deployment on Kubernetes using Kubeflow. Which component should the auditor examine to ensure that the pipeline steps are reproducible?
When scoping an AI audit engagement, which TWO of the following documents should the auditor request to understand the AI model's governance structure?
An audit team must verify that a credit-scoring model's predictions can be explained to a regulator on a case-by-case basis. The data science team used a gradient-boosted tree ensemble. Which technique should the auditor recommend to produce locally faithful explanations of individual decisions?
An AI audit team is validating a fraud-detection model deployed through a REST API. The model card claims 94% recall, but the auditor wants independent evidence that the live endpoint behaves as documented. The team has read access to the model registry and the API logs, but cannot access the training pipeline. Which technique should the auditor use to validate the deployed model's behavior?
An auditor needs to confirm that a deployed model in production is bit-for-bit identical to the artifact that passed validation. Which artifact should the auditor use to verify integrity?
An auditor is reviewing an AI-based loan underwriting system and wants to verify that the model's predictions are stable when small, non-semantic changes are made to input features. The auditor plans to submit the same applicant profile with trivial formatting variations. Which auditing technique does this describe?
An auditor is examining a computer vision model used for medical image triage. The vendor provides only a compiled binary and no architecture documentation. The auditor wants to estimate how much the model's output changes when individual pixels are altered slightly, in order to assess decision boundary sharpness. Which technique is most appropriate?
An auditor is testing whether a recommendation model leaks information about individual users in its training set. The team exposes only top-N ranked outputs through the API. Which technique is most appropriate to estimate membership inference risk under this constraint?
An auditor is assessing an AI recruitment screening tool that ranks candidates. The auditor needs to gather evidence that the model's decisions can be explained to rejected applicants and to a regulator. Which TWO techniques should the auditor apply to produce local, case-level explanations for individual candidate rankings? (Choose two.)
During an audit of a natural language processing system, the auditor needs to determine whether a fine-tuned model reproduces verbatim passages from its training corpus. Which technique should the auditor apply to test for training-data extraction?
An auditor is evaluating a generative AI customer service assistant that produces free-text responses. The auditor wants to systematically test whether the assistant can be induced to reveal its system prompt or produce prohibited content. Which technique should the auditor use?