AI Security and Responsible AI Practices

Introduction
AI Security and Responsible AI Practices Introduction

Lesson 1 Overview of AI and ML Implementations
Learning objectives
Delving into supervised, unsupervised, and reinforcement learning
Diving into applications and use cases
Strategies in preprocessing and feature engineering
Navigating through popular and traditional ML algorithms
Exploring model evaluation and validation

Lesson 2 Generative AI and Large Language Models (LLMs)
Learning objectives
Introduction to generative AI
Delving into large language models (LLMs)
Exploring examples of AI applications we use on a daily basis
Going beyond ChatGPT, MidJourney, LLaMA
Exploring Hugging Face, LangChain Hub, and other AI model and dataset sharing hubs
Modern AI model training environments
Introducing LangChain, templates, and agents
Fine tuning AI Models using LoRA and QLoRA
Introducing retrieval-augmented generation (RAG)

Lesson 3 Fundamentals of AI and ML Security
Learning objectives
Importance of security in AI and ML systems
OWASP top 10 risks for LLM applications
Exploring prompt injection attacks
Surveying data poisoning attacks
Understanding insecure output handling
Discussing insecure plugin design
Understanding excessive agency
Exploring model theft attacks
Understanding overreliance of AI systems

Lesson 4 How Attackers Are Using AI to Perform Attacks
Learning objectives
Exploring the MITRE ATLAS framework
AI supply chain security
Automated vulnerability discovery and creating exploits at scale
Intelligent data harvesting, OSINT, automating phishing, and social engineering attacks
Exploring examples of deepfakes and synthetic media
Dynamic obfuscation of attack vectors

Lesson 5 AI System and Infrastructure Security
Learning objectives
Secure development practices
Monitoring and auditing
Software Bill of Materials (SBOMs) and AI Bill of Materials (AI BOMs)
Using CSAF and VEX to accelerate vulnerability management

Lesson 6 Privacy and AI Fundamentals
Learning objectives
Understanding key privacy considerations in AI implementations
Bias and fairness in AI and ML systems
Transparency and accountability
Understanding differential privacy
Exploring secure multi-party computation (SMPC)
Understanding homomorphic encryption
Understanding the AI data lifecycle management
Delving into federated learning

Lesson 7 AI Ethics
Learning objectives
Ethical considerations in AI development
Responsible AI frameworks
Policy frameworks
Exploring strategies to mitigate bias

Lesson 8 Legal and Regulatory Compliance
Learning objectives
Overview of upcoming regulations and guidelines
Ensuring compliance in AI and ML systems
Case studies and best practices

Module 1 Fundamentals of AI and ML
Module introduction

Module 2 AI and ML Security
Module introduction

Module 3 Privacy and Ethical Considerations
Module introduction

Summary
AI Security and Responsible AI Practices Summary