Introduction

Welcome to my learning journey on AI/ML Security. This series contains daily notes, LinkedIn posts, and learnings.

👉 Start reading from Day 1 AL vs ML vs DL

🧠 Phase 1: Build a Solid Foundation (Days 1–20)

Goal: Understand the basics of AI/ML so you can later secure it

Topics

  • What is AI, ML, DL? Differences?

  • Supervised, Unsupervised, Reinforcement Learning

  • Common ML algorithms (Linear Regression, Decision Trees, SVM, etc.)

  • Overfitting, Underfitting, Bias-Variance Tradeoff

  • Feature engineering and model evaluation (accuracy, precision, recall)

  • Basics of Neural Networks

  • Introduction to LLMs and Transformers

💡 Daily Post Tip: “Here’s how [topic] could lead to a security issue…”

🔐 Phase 2: AI/ML Threat Landscape (Days 21–40)

Goal: Learn all the ways AI/ML systems can be attacked or go wrong

Topics

  • Model inversion attacks

  • Membership inference attacks

  • Adversarial ML (e.g., image perturbations)

  • Data poisoning and backdooring

  • Supply chain attacks on ML (libraries, datasets)

  • Attacks on training/inference pipelines

  • LLM-specific issues (prompt injection, jailbreaks, data leakage)

  • Privacy risks in federated learning

NextAbout Me

Last updated