“GOOGLE CLOUD PROFESSIONAL MACHINE LEARNING ENGINEER EXAM OBJECTIVES COVERED IN THIS CHAPTER:

2.1 Exploring and preprocessing organization‐wide data (e.g., Cloud Storage, BigQuery, Cloud Spanner, Cloud SQL, Apache Spark, Apache Hadoop). Considerations include:

Privacy implications of data usage and/or collection (e.g., handling sensitive data such as personally identifiable information [PII] and protected health information [PHI])

2.2 Model prototyping using Jupyter notebooks. Considerations include:

Applying security best practices in Vertex AI Workbench

4.2 Scaling online model serving. Considerations include:

Vertex AI public and private endpoints

6.1 Identifying risks to ML solutions. Considerations include:

Building secure ML systems (e.g., protecting against unintentional exploitation of data or models, hacking)”

Building Secure ML Systems

Encryption at Rest

Authenticated Encryption with Associated Data - AEAD BigQuery Encryption functions: https://cloud.google.com/bigquery/docs/aead-encryption-concepts

Server-side encryption vs client-side encryption

Encryption in Transit

Transport Layer Security (TLS)

Encryption in Use

• Confidential Computing - protects data in memory from compromise by encrypting it while it is being processed
• Confidential VMs and Confidential GKE Nodes