# 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](broken://pages/x17bfc54XQLohRDeZVWQ)

## 🧠 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:**\
\&#xNAN;*“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


---

# Agent Instructions: Querying This Documentation

If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://arif-playbook.gitbook.io/100-days-of-ai-sec/readme.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
The response will contain a direct answer to the question and relevant excerpts and sources from the documentation.

Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.