Defending and Deploying AI by Pearson
15hIntermediate2026-02-19
Authors
Pearson
Course details
In this course, learn how to harness the power of cutting-edge AI tools for enhanced cybersecurity, networking, and programming. Join Omar Santos—a distinguished engineer at Cisco, recognized author, and expert in AI cybersecurity—as he outlines the skills and know-how required to get up and running with building and deploying secure AI models, without writing a single line of code. Learn how to master AI tools for dynamic information retrieval, advanced automation, and more. Explore crucial security measures for AI deployments, including LLM security, prompt injection, and red team AI models. Create secure AI research environments, both home- and cloud-based, with guidance on hardware, software, and cost management. Along the way, you’ll get the chance to test out your newly acquired skills in real-world hands-on activities.
Concepts
Introduction
- Introduction
Introduction to AI-Powered Tools
- Learning objectives
- Overview of the evolution of AI-driven tools
- Large language models (LLMs) and small language models (SLMs)
- Introducing LangChain, LangGraph, Llama Index, and other orchestration frameworks
- An overview of open-source AI models and Hugging Face
- Introducing retrieval augmented generation (RAG)
- Introducing embedding models
- Introducing vector databases - pgvector, Chroma, MongoDB Atlas Vector Search, and others
- Introducing semantic search
Using AI for Cybersecurity
- Learning objectives
- Accelerating network security tasks with AI
- Prompt engineering for cybersecurity
- Securing AI implementations
- Exploring network security processes incorporating AI tools
Using AI for Software Development
- Learning objectives
- Exploring how AI is revolutionizing software development
- Surveying GitHub Copilot, Cursor, and Cody
- Exploring the CODEX model
- Generating code from a prompt
- Explaining existing code
- Generating comments
- Prompt engineering for software development
Using AI for Networking
- Learning objectives
- Exploring how AI is revolutionizing networking
- Using GitHub Copilot for programming tasks related to networking
- Exploring AI models for networking use cases
- Prompt engineering for networking
Future Trends and Additional Emerging Technologies
- Learning objectives
- Exploring additional applications of AI in emerging technologies
- Regulatory and policy frameworks
- Staying updated on advancements in AI and cybersecurity
AI-Enabled Programming, Networking, and Cybersecurity - Summary
- Summary
Securing Generative AI - Introduction
- Introduction
Introduction to AI Threats and LLM Security
- Learning objectives
- Understanding the significance of LLMs in the AI landscape
- Exploring the resources for this course - GitHub repositories and others
- Introducing retrieval-augmented generation (RAG)
- Understanding the OWASP Top 10 risks for LLMs
- Exploring the MITRE ATLAS (Adversarial Threat Landscape for Artificial-Intelligence Systems) framework
- Understanding the NIST taxonomy and terminology of attacks and mitigations
Understanding Prompt Injection and Insecure Output Handling
- Learning objectives
- Defining prompt injection attacks
- Exploring real-life prompt injection attacks
- Using ChatML for OpenAI API calls to indicate to the LLM the source of prompt input
- Enforcing privilege control on LLM access to back-end systems
- Best practices around API tokens for plugins, data access, and function-level permissions
- Understanding insecure output handling attacks
- Using the OWASP ASVS to protect against insecure output handling
Training Data Poisoning, Model Denial of Service, and Supply Chain Vulnerabilities
- Learning objectives
- Understanding training data poisoning attacks
- Exploring model denial of service attacks
- Understanding the risks of the AI and ML supply chain
- Best practices when using open-source models from Hugging Face and other sources
- Securing Amazon Bedrock, SageMaker, Microsoft Azure AI Services, and other environments
Sensitive Information Disclosure, Insecure Plugin Design, and Excessive Agency
- Learning objectives
- Understanding sensitive information disclosure
- Exploiting insecure plugin design
- Avoiding excessive agency
Overreliance, Model Theft, and Red Teaming AI Models
- Learning objectives
- Understanding overreliance
- Exploring model theft attacks
- Understanding red teaming of AI models
Protecting Retrieval-Augmented Generation (RAG) Implementations
- Learning objectives
- Understanding the RAG, LangChain, Llama Index, and AI orchestration
- Securing embedding models
- Securing vector databases
- Monitoring and incident response
Securing Generative AI - Summary
- Summary
Build Your Own AI Lab - Introduction
- Introduction
Introduction to AI Labs and Sandboxes
- Learning objectives
- Overview of AI labs and sandboxes - Home-based vs. cloud-based
- Choosing the right hardware - GPUs, CPUs, and memory
- Building or buying prebuilt systems
- Choosing the operating system - Linux, Windows, and macOS
- Surveying essential software - Python, Anaconda, Jupyter Notebooks, and other frameworks
- Introducing Hugging Face
- Introducing Ollama
- Installing Ollama
- Ollama integrations
- Exploring the Ollama REST API
- Exploring RAG
- Leveraging RAGFlow
Cloud-Based AI Labs and Sandboxes
- Learning objectives
- Advantages and disadvantages of cloud AI labs and sandboxes
- Introducing Amazon Bedrock
- Surveying Amazon SageMaker
- Exploring Google Vertex AI
- Using Microsoft Azure AI Foundry
- Discussing cost management and security
- Using Terraform to deploy Ollama in the cloud
Integrating and Leveraging AI Environments
- Learning objectives
- Using hybrid AI labs - combining home and cloud resources
- Synchronizing data and projects
- Leveraging the strengths of both environments
- Running open-source models available on Hugging Face
- Introducing LangChain
- Introducing LlamaIndex
- Understanding embedding models
- Using vector databases
Advanced Topics
- Learning objectives
- Leveraging LangSmith and LangGraph
- Using fine-tuning frameworks
- High-performance computing and edge AI
Build Your Own AI Lab - Summary
- Summary
AI Agents and Agentic RAG for Cybersecurity - Introduction
- Introduction
Introduction to RAG in Cybersecurity
- Learning objectives
- The essentials of RAG
- Exploring the GitHub repositories and additional resources
- Embeddings and embedding models
- Indexing techniques
- Vector databases
- Chunking strategies
- RAG vs. fine-tuning
- RAG, RAG Fusion, and RAPTOR
- Running open-weight models with Ollama
- Exploring Open WebUI and other Ollama plugins
- Introduction to AI agents and agentic implementations
- Introduction to agentic RAG
- Introducing the Model Context Protocol (MCP)
- Introducing A2A and AGNTCY
Introducing LangChain, LangGraph, and LLamaIndex
- Learning objectives
- Introducing LangChain
- LangChain vs. LlamaIndex
- Prompt templates and system prompts
- Introducing LangSmith
Prompt Engineering, Prompt Chains, and RAG Examples
- Learning objectives
- Mastering prompt engineering
- Exploring basic prompt chain examples
- Creating prompt branching chains
- Exploring parallel prompt chains
- Creating a basic RAG application
- Creating a complete RAG application
AI Agents and Agentic RAG for Cybersecurity - Summary
- Learning objectives
- Introduction to AI agent frameworks
- Surveying CrewAI
- Introducing LangGraph
- Exploring examples of LangGraph in action
- Exploring an example of agents with MCP servers
- Securing agentic implementations
- Summary