Vertex AI and Generative AI Security

Vertex AI and Generative AI SecurityVAIGASGOGoogleGO-VAIGAS1.0<ul> <li>Establish foundational knowledge of Vertex AI and its security challenges.</li><li>Implement identity and access control measures to restrict access to Vertex AI resources.</li><li>Configure encryption strategies and protect sensitive information.</li><li>Enable logging, monitoring, and alerting for real-time security oversight of Vertex AI operations.</li><li>Identify and mitigate unique security threats associated with generative AI.</li><li>Apply testing techniques to validate and secure generative AI model responses.</li><li>Implement best practices for securing data sources and responses within Retrieval-Augmented Generation (RAG) systems.</li><li>Establish foundational knowledge of AI Safety.</li></ul>Fundamental knowledge of machine learning, in particular generative AI, and basic understanding of security on Google Cloud.AI practitioners, security professionals, and cloud architects<h4>Module 01 - Introduction to Vertex AI Security Principles</h4> Topics <ul> <li>Google Cloud Security</li><li>Vertex AI components</li><li>Vertex AI Security concerns</li></ul> Objectives <ul> <li>Review Google Cloud Security fundamentals.</li><li>Establish a foundational understanding of Vertex AI.</li><li>Enumerate the security concerns related to Vertex AI features and components.</li></ul> Activities <ul> <li>Lab: Vertex AI: Training and Serving a Custom Model</li></ul> <h4>Module 02 - Identity and Access Management (IAM) in Vertex AI</h4> Topics <ul> <li>Overview of IAM in Google Cloud</li></ul> Objectives <ul> <li>Control access with Identity Access Management.</li><li>Simplify permission using organization hierarchies and policies.</li><li>Use service accounts for least privileged access.</li></ul> Activities <ul> <li>Lab: Service Accounts and Roles: Fundamentals</li></ul> <h4>Module 03 - Data Security and Privacy</h4> Topics <ul> <li>Data encryption</li><li>Protecting Sensitive Data</li><li>VPC Service Controls</li><li>Disaster recovery planning</li></ul> Objectives <ul> <li>Configure encryption at rest and in-transit.</li><li>Encrypt data using customer-managed encryption keys.</li><li>Protect sensitive data using the Data Loss Prevention service.</li><li>Prevent exfiltration of data using VPC Service Controls.</li><li>Architect systems with disaster recovery in mind.</li></ul> Activities <ul> <li>Lab: Getting Started with Cloud KMS</li><li>Lab: Creating a De-identified Copy of Data in Cloud Storage</li></ul><h4>Module 04 - Securing Vertex AI Endpoints and model deployment</h4> Topics <ul> <li>Network security</li><li>Securing model endpoints</li></ul> Objectives <ul> <li>Deploy ML models using model endpoints.</li><li>Secure model endpoints.</li></ul> Activities <ul> <li>Lab: Configuring Private Google Access and Cloud NAT</li></ul><h4>Module 05 - Monitoring and logging in Vertex AI</h4> Topics <ul> <li>Logging</li><li>Monitoring</li></ul> Objectives <ul> <li>Write to and analyze logs.</li><li>Set up monitoring and alerting.</li></ul><h4>Module 06 - Security risks in generative AI applications</h4> Topics <ul> <li>Overview of gen AI security risks</li><li>Overview of AI Safety</li><li>Prompt security</li><li>LLM safeguards</li></ul> Objectives <ul> <li>Identify security risks specific to LLMs and gen AI applications.</li><li>Understand methods for mitigating prompt hacking and injection attacks.</li><li>Explore the fundamentals of securing generative AI models and applications.</li><li>Introduce fundamentals of AI Safety.</li></ul> Activities <ul> <li>Lab: Safeguarding with Vertex AI Gemini API</li><li>Lab: Gen AI & LLM Security for Developers</li></ul><h4>Module 07 - Testing and evaluating generative AI model responses</h4> Topics <ul> <li>Testing generative AI model responses.</li><li>Evaluating model responses.</li><li>Fine-Tuning LLMs.</li></ul> Objectives <ul> <li>Implement best practices for testing model responses.</li><li>Apply techniques for improving response security in gen AI applications</li></ul> Activities <ul> <li>Lab: Measure Gen AI Performance with the Generative AI Evaluation Service</li><li>Lab: Unit Testing Generative AI Applications</li></ul><h4>Module 08 - Securing Retrieval-Augmented Generation (RAG) systems</h4> Topics <ul> <li>Fundamentals of Retrieval-Augmented Generation</li><li>Security in RAG systems</li></ul> Objectives <ul> <li>Understand RAG architecture and security implications.</li><li>Implement best practices for grounding and securing data sources in RAG systems.</li></ul> Activities <ul> <li>Lab: Multimodal Retrieval Augmented Generation (RAG) Using the Vertex AI Gemini API</li><li>Lab: Introduction to Function Calling with Gemini</li></ul>- Establish foundational knowledge of Vertex AI and its security challenges. - Implement identity and access control measures to restrict access to Vertex AI resources. - Configure encryption strategies and protect sensitive information. - Enable logging, monitoring, and alerting for real-time security oversight of Vertex AI operations. - Identify and mitigate unique security threats associated with generative AI. - Apply testing techniques to validate and secure generative AI model responses. - Implement best practices for securing data sources and responses within Retrieval-Augmented Generation (RAG) systems. - Establish foundational knowledge of AI Safety.Fundamental knowledge of machine learning, in particular generative AI, and basic understanding of security on Google Cloud.AI practitioners, security professionals, and cloud architectsModule 01 - Introduction to Vertex AI Security Principles Topics - Google Cloud Security - Vertex AI components - Vertex AI Security concerns Objectives - Review Google Cloud Security fundamentals. - Establish a foundational understanding of Vertex AI. - Enumerate the security concerns related to Vertex AI features and components. Activities - Lab: Vertex AI: Training and Serving a Custom Model Module 02 - Identity and Access Management (IAM) in Vertex AI Topics - Overview of IAM in Google Cloud Objectives - Control access with Identity Access Management. - Simplify permission using organization hierarchies and policies. - Use service accounts for least privileged access. Activities - Lab: Service Accounts and Roles: Fundamentals Module 03 - Data Security and Privacy Topics - Data encryption - Protecting Sensitive Data - VPC Service Controls - Disaster recovery planning Objectives - Configure encryption at rest and in-transit. - Encrypt data using customer-managed encryption keys. - Protect sensitive data using the Data Loss Prevention service. - Prevent exfiltration of data using VPC Service Controls. - Architect systems with disaster recovery in mind. Activities - Lab: Getting Started with Cloud KMS - Lab: Creating a De-identified Copy of Data in Cloud Storage Module 04 - Securing Vertex AI Endpoints and model deployment Topics - Network security - Securing model endpoints Objectives - Deploy ML models using model endpoints. - Secure model endpoints. Activities - Lab: Configuring Private Google Access and Cloud NAT Module 05 - Monitoring and logging in Vertex AI Topics - Logging - Monitoring Objectives - Write to and analyze logs. - Set up monitoring and alerting. Module 06 - Security risks in generative AI applications Topics - Overview of gen AI security risks - Overview of AI Safety - Prompt security - LLM safeguards Objectives - Identify security risks specific to LLMs and gen AI applications. - Understand methods for mitigating prompt hacking and injection attacks. - Explore the fundamentals of securing generative AI models and applications. - Introduce fundamentals of AI Safety. Activities - Lab: Safeguarding with Vertex AI Gemini API - Lab: Gen AI & LLM Security for Developers Module 07 - Testing and evaluating generative AI model responses Topics - Testing generative AI model responses. - Evaluating model responses. - Fine-Tuning LLMs. Objectives - Implement best practices for testing model responses. - Apply techniques for improving response security in gen AI applications Activities - Lab: Measure Gen AI Performance with the Generative AI Evaluation Service - Lab: Unit Testing Generative AI Applications Module 08 - Securing Retrieval-Augmented Generation (RAG) systems Topics - Fundamentals of Retrieval-Augmented Generation - Security in RAG systems Objectives - Understand RAG architecture and security implications. - Implement best practices for grounding and securing data sources in RAG systems. Activities - Lab: Multimodal Retrieval Augmented Generation (RAG) Using the Vertex AI Gemini API - Lab: Introduction to Function Calling with Gemini2 days1495.002065.001500.001320.001500.001500.001500.001550.001300.001500.00