on-demand course

Securing Generative AI

with Omar Santos

November 2024

Intermediate

3h 40m

English

Pearson

Closed Captioning available in English

Watch now

Unlock full access

Includes

Earns Badge

Course outline

Securing Generative AI: Introduction
3m 0s
Learning objectives
1m 18s
1.1 Understanding the Significance of LLMs in the AI Landscape
7m 6s
1.2 Exploring the Resources for this Course - GitHub Repositories and Others
2m 54s
1.3 Introducing Retrieval Augmented Generation (RAG)
12m 25s
1.4 Understanding the OWASP Top-10 Risks for LLMs
5m 46s
1.5 Exploring the MITRE ATLAS™ (Adversarial Threat Landscape for Artificial-Intelligence Systems) Framework
5m 39s
1.6 Understanding the NIST Taxonomy and Terminology of Attacks and Mitigations
7m 9s
Learning objectives
1m 2s
2.1 Defining Prompt Injection Attacks
11m 42s
2.2 Exploring Real-life Prompt Injection Attacks
3m 57s
2.3 Using ChatML for OpenAI API Calls to Indicate to the LLM the Source of Prompt Input
10m 5s
2.4 Enforcing Privilege Control on LLM Access to Backend Systems
6m 10s
2.5 Best Practices Around API Tokens for Plugins, Data Access, and Function-level Permissions
3m 2s
2.6 Understanding Insecure Output Handling Attacks
3m 22s
2.7 Using the OWASP ASVS to Protect Against Insecure Output Handling
4m 43s
Learning objectives
47s
3.1 Understanding Training Data Poisoning Attacks
4m 27s
3.2 Exploring Model Denial of Service Attacks
3m 12s
3.3 Understanding the Risks of the AI and ML Supply Chain
8m 34s
3.4 Best Practices when Using Open-Source Models from Hugging Face and Other Sources
12m 46s
3.5 Securing Amazon BedRock, SageMaker, Microsoft Azure AI Services, and Other Environments
16m 5s
Learning objectives
1m 4s
4.1 Understanding Sensitive Information Disclosure
2m 53s
4.2 Exploiting Insecure Plugin Design
3m 12s
4.3 Avoiding Excessive Agency
3m 46s
Learning objectives
47s
5.1 Understanding Overreliance
5m 17s
5.2 Exploring Model Theft Attacks
4m 57s
5.3 Understanding Red Teaming of AI Models
13m 34s
Learning objectives
1m 6s
6.1 Understanding the RAG, LangChain, Llama Index, and AI Orchestration
17m 21s
6.2 Securing Embedding Models
9m 39s
6.3 Securing Vector Databases
12m 1s
6.4 Monitoring and Incident Response
7m 50s
Securing Generative AI: Summary
1m 41s

Content preview from Securing Generative AI

3.4 Best Practices when Using Open-Source Models from Hugging Face and Other Sources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

Start your free trial

Generative AI Security Conference

Omar Santos

AI Security and Responsible AI Practices

Omar Santos / Dr. Petar Radanliev

The Rise of AI Agents: Integrating AI, Blockchain Technologies, and Quantum Computing

Petar Radanliev

AI Agents with MCP

Kyle Stratis

Publisher Resources

ISBN: 9780135401804

Securing Generative AI

with Omar Santos

Introduction

Lesson 1: Introduction to AI Threats and LLM Security

Lesson 2: Understanding Prompt Injection & Insecure Output Handling

Lesson 3: Training Data Poisoning, Model Denial of Service & Supply Chain Vulnerabilities

Lesson 4: Sensitive Information Disclosure, Insecure Plugin Design, and Excessive Agency

Lesson 5: Overreliance, Model Theft, and Red Teaming AI Models

Lesson 6: Protecting Retrieval Augmented Generation (RAG) Implementations

Summary

Content preview from Securing Generative AI

3.4 Best Practices when Using Open-Source Models from Hugging Face and Other Sources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.

You might also like

Generative AI Security Conference

AI Security and Responsible AI Practices

The Rise of AI Agents: Integrating AI, Blockchain Technologies, and Quantum Computing

AI Agents with MCP

Publisher Resources

Introduction

Lesson 1: Introduction to AI Threats and LLM Security

Lesson 2: Understanding Prompt Injection & Insecure Output Handling

Lesson 3: Training Data Poisoning, Model Denial of Service & Supply Chain Vulnerabilities

Lesson 4: Sensitive Information Disclosure, Insecure Plugin Design, and Excessive Agency

Lesson 5: Overreliance, Model Theft, and Red Teaming AI Models

Lesson 6: Protecting Retrieval Augmented Generation (RAG) Implementations

Summary

Content preview from Securing Generative AI

3.4 Best Practices when Using Open-Source Models from Hugging Face and Other Sources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,and much more.

You might also like

Generative AI Security Conference

AI Security and Responsible AI Practices

The Rise of AI Agents: Integrating AI, Blockchain Technologies, and Quantum Computing

AI Agents with MCP

Publisher Resources

Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.