51. A company is testing the security of a foundation model (FM). During testing, the company wants to get around the safety features and make harmful content.
Which security technique is this an example of?
A. Fuzzing training data to find vulnerabilities
B. Denial of service (DoS)
C. Penetration testing with authorization
D. Jailbreak
Answer
D
52. A company needs to use Amazon SageMaker for model training and inference. The company must comply with regulatory requirements to run SageMaker jobs in an isolated environment without internet access.
Which solution will meet these requirements?
A. Run SageMaker training and inference by using SageMaker Experiments.
B. Run SageMaker training and Inference by using network Isolation.
C. Encrypt the data at rest by using encryption for SageMaker geospatial capabilities.
D. Associate appropriate AWS Identity and Access Management (IAM) roles with the SageMaker jobs.
Answer
B
53. An ML research team develops custom ML models. The model artifacts are shared with other teams for integration into products and services. The ML team retains the model training code and data. The ML team wants to build a mechanism that the ML team can use to audit models.
Which solution should the ML team use when publishing the custom ML models?
A. Create documents with the relevant information. Store the documents in Amazon S3.
B. Use AWS AI Service Cards for transparency and understanding models.
C. Create Amazon SageMaker Model Cards with intended uses and training and inference details.
D. Create model training scripts. Commit the model training scripts to a Git repository.
Answer
C
54. A software company builds tools for customers. The company wants to use AI to increase software development productivity.
Which solution will meet these requirements?
A. Use a binary classification model to generate code reviews.
B. Install code recommendation software in the company’s developer tools.
C. Install a code forecasting tool to predict potential code issues.
D. Use a natural language processing (NLP) tool to generate code.
Answer
B
55. A retail store wants to predict the demand for a specific product for the next few weeks by using the Amazon SageMaker DeepAR forecasting algorithm.
Which type of data will meet this requirement?
A. Text data
B. Image data
C. Time series data
D. Binary data
Answer
C
56. A large retail bank wants to develop an ML system to help the risk management team decide on loan allocations for different demographics.
What must the bank do to develop an unbiased ML model?
A. Reduce the size of the training dataset.
B. Ensure that the ML model predictions are consistent with historical results.
C. Create a different ML model for each demographic group.
D. Measure class imbalance on the training dataset. Adapt the training process accordingly.
Answer
D
57. Which prompting technique can protect against prompt injection attacks?
A. Adversarial prompting
B. Zero-shot prompting
C. Least-to-most prompting
D. Chain-of-thought prompting
Answer
A
58. A company has fine-tuned a large language model (LLM) to answer questions for a help desk. The company wants to determine if the fine-tuning has enhanced the model’s accuracy.
Which metric should the company use for the evaluation?
A. Precision
B. Time to first token
C. F1 score
D. Word error rate
Answer
C
59. A company is developing a mobile ML app that uses a phone’s camera to diagnose and treat insect bites. The company wants to train an image classification model by using a diverse dataset of insect bite photos from different genders, ethnicities, and geographic locations around the world.
Which principle of responsible AI does the company demonstrate in this scenario?
A. Fairness
B. Explainability
C. Governance
D. Transparency
Answer
A
60. A company makes forecasts each quarter to decide how to optimize operations to meet expected demand. The company uses ML models to make these forecasts.
An AI practitioner is writing a report about the trained ML models to provide transparency and explainability to company stakeholders.
What should the AI practitioner include in the report to meet the transparency and explainability requirements?
A. Code for model training
B. Partial dependence plots (PDPs)
C. Sample data for training
D. Model convergence tables
Answer
B