Part 1: Classical Adversarial Thinking

💡 Start Here: setup_instructions.md → recitation1.ipynb → assignment1.ipynb

🎯 Learning Overview

Welcome to Part 1! In this module, you will learn how to think like an adversary. You’ll explore one of the most fundamental vulnerabilities in computer systems: hash collision attacks. You’ll learn how attackers can exploit weaknesses in hash functions to cause denial of service, degrade performance, and compromise system security.

🚀 Getting Started

Step 1: Setup Your Environment

Follow the instructions in setup_instructions.md to install required dependencies and set up your development environment.

Step 2: Complete the Recitation

Work through recitation1.ipynb to understand the concepts through interactive demonstrations.

Step 3: Complete the Assignment

Implement your solutions in assignment1.ipynb and submit your completed notebook plus analysis report.

⏱️ Time Expectations

Recitation: 30-60 minutes (interactive learning)
Assignment: 60 minutes (implementation and analysis)
Total: 1.5-2 hours for complete mastery

🔗 But why? I thought this was an AI course!

You will learn the “AI” part of adversarial AI in later parts. We are starting with the “adversarial” part. This module introduces fundamental concepts that appear throughout adversarial AI:

Adversarial Examples: Like hash collisions, these exploit mathematical properties of algorithms
Robustness vs Performance: The same trade-offs appear in ML model security
Adaptive Attacks: Sophisticated attackers adapt to defenses, requiring adaptive defenses
Statistical Analysis: Understanding attack patterns requires statistical thinking