support@Free-Braindumps.com
Register Login
Cisco
CompTIA
ISC
EC-Council
EXIN
Fortinet
ITIL
Juniper
Microsoft
VMware
Avaya
SAP
Google
NVIDIA
Salesforce
Amazon
Palo Alto Networks
ISC2
CrowdStrike
Anthropic
All Vendors
  1. Home
  2. Exams
  3. Google
  4. PROFESSIONAL MACHINE LEARNING ENGINEER

Free PROFESSIONAL MACHINE LEARNING ENGINEER Exam Braindumps
Professional Machine Learning Engineer Questions 71–75 (page: 16)

Updated On: 25-Oct-2026
Page 16 of 82
PDF with 402 Questions

You have fine-tuned a Gemini model to act as a customer service agent for a bank. You need to proactively identify potential security risks, specifically the model's vulnerability to adversarial jailbreak attacks. You want to perform this assessment systematically by generating adversarial prompts and scoring the model's responses using a fully managed service.
What should you do?

  1. Run the model evaluation service. Configure the job to use adversarial testing to identify jailbreak attempts and determine the model's refusal rate.
  2. Create an Agent Platform batch prediction job using a dataset of historical jailbreak prompts. Analyze the output metadata to calculate the percentage of responses blocked by the Agent Platform safety filters.
  3. Deploy the model to an Agent Platform endpoint behind Model Armor. Review the Cloud Logging entries generated by Model Armor to identify which incoming requests trigger the jailbreak filter.
  4. Configure Sensitive Data Protection to inspect the adversarial prompts. Create a custom infoType detector to identify patterns associated with jailbreak attacks and flag the model's responses for review.

Answer(s): A

Explanation:

The Gen AI evaluation service in Agent Platform provides a managed framework for systematically assessing generative AI models, including their safety and robustness against adversarial attacks. By configuring adversarial testing with generated jailbreak prompts, you can evaluate how effectively the fine-tuned Gemini model resists attempts to bypass its safety instructions. Measuring the model's refusal rate helps quantify its resistance to jailbreak attacks, identify security vulnerabilities, and guide improvements before production deployment.


Reference:

https://developers.googleblog.com/agent-and-model-evaluations-in-gemini-enterprise-agent-platfor m-are-now-ga/
https://docs.cloud.google.com/gemini-enterprise-agent-platform/models/evaluation-overview?hl=en



You need to deploy a scikit-learn classification model to production. The model must be able to serve requests 24/7, and you expect millions of requests per second to the production application from 8 am to 7 pm. You need to minimize the cost of deployment.
What should you do?

  1. Deploy an online Vertex AI prediction endpoint. Set the max replica count to 1
  2. Deploy an online Vertex AI prediction endpoint. Set the max replica count to 100
  3. Deploy an online Vertex AI prediction endpoint with one GPU per replica. Set the max replica count to 1
  4. Deploy an online Vertex AI prediction endpoint with one GPU per replica. Set the max replica count to 100

Answer(s): B



You are responsible for building a unified analytics environment across a variety of on-premises data marts. Your company is experiencing data quality and security challenges when integrating data across the servers, caused by the use of a wide range of disconnected tools and temporary solutions. You need a fully managed, cloud-native data integration service that will lower the total cost of work and reduce repetitive work. Some members on your team prefer a codeless interface for building Extract, Transform, Load (ETL) process.
Which service should you use?

  1. Dataflow
  2. Dataprep
  3. Apache Flink
  4. Cloud Data Fusion

Answer(s): D



You have developed a BigQuery ML model that predicts customer churn, and deployed the model to Vertex AI Endpoints. You want to automate the retraining of your model by using minimal additional code when model feature values change. You also want to minimize the number of times that your model is retrained to reduce training costs.
What should you do?

  1. 1 Enable request-response logging on Vertex AI Endpoints
    2. Schedule a TensorFlow Data Validation job to monitor prediction drift
    3. Execute model retraining if there is significant distance between the distributions
  2. 1. Enable request-response logging on Vertex AI Endpoints
    2. Schedule a TensorFlow Data Validation job to monitor training/serving skew
    3. Execute model retraining if there is significant distance between the distributions
  3. 1. Create a Vertex AI Model Monitoring job configured to monitor prediction drift
    2. Configure alert monitoring to publish a message to a Pub/Sub queue when a monitoring alert is detected
    3. Use a Cloud Function to monitor the Pub/Sub queue, and trigger retraining in BigQuery
  4. 1. Create a Vertex AI Model Monitoring job configured to monitor training/serving skew
    2. Configure alert monitoring to publish a message to a Pub/Sub queue when a monitoring alert is detected
    3. Use a Cloud Function to monitor the Pub/Sub queue, and trigger retraining in BigQuery

Answer(s): D



You are responsible for managing the recommendation engine on an ecommerce website. The current model is deployed on a public Agent Platform endpoint and is actively serving production traffic. You have developed an updated version of the model and registered the model in Model Registry. You need to perform an A/B test to compare the new model’s performance to the current model.
You plan to implement a traffic split, routing 10% of all incoming production requests to the new model and sending the remaining 90% to the current model. You want this transition to be transparent, and require no modifications to the client application that calls the endpoint.
What should you do?

  1. Deploy the new model to a serverless Cloud Run service. Implement logic in the client application that routes 10% of user requests to the Cloud Run service and the rest to the original endpoint.
  2. Deploy the new model to the Agent Platform endpoint where the current model is deployed. Configure the endpoint’s traffic split to allocate 10% of user requests to the new model.
  3. Create two separate Agent Platform Pipelines, one for each model version. Use Agent Platform Experiments to run both pipelines simultaneously. Configure the experiment to send 10% of user requests to the new model’s pipeline and the rest to the production model’s pipeline.
  4. Deploy the new model to a new Agent Platform endpoint. Configure Cloud Load Balancing to send 10% of user requests to the new endpoint and the rest to the original endpoint.

Answer(s): B

Explanation:

Deploying both model versions to the same Agent Platform endpoint allows the endpoint’s native traffic-splitting configuration to route 10% of prediction requests to the new model and 90% to the current model. The endpoint URL remains unchanged, so the A/B test requires no client application modifications.



  PDF
Viewing page 16 of 82
Viewing questions 76 - 80 out of 402 questions


Post your Comments and Discuss Google PROFESSIONAL MACHINE LEARNING ENGINEER exam prep with other Community members:

AI Tutor AI Tutor 👋 I’m here to help!