AI Models & Data.
Follow the data, understand the model, and learn what evidence helps you trust an AI system.
Read the room notesTask by task
Six notes covering tasks 1–5 and 7. Task 6 Practical is not included in the published notes.
- 01
Introduction
Follow the journey from collected data to a deployed model, and see why security starts before the first answer.
- 02
Training Data
Follow training data from its source to a model, and learn how to check quality, permissions, privacy, and hidden secrets.
- 03
Building the Model
Understand training rounds, fair testing, smaller models, and learning across devices without assuming that private data is automatically safe.
- 04
The Inheritance Problem
Understand what a fine-tuned model inherits, why safety can change, and how model history helps explain risk.
- 05
The Black Box Problem
Learn what model inspection can reveal, how to read a model card, and why documentation needs supporting evidence.
- 07
Conclusion
Connect data history, training choices, inherited behavior, and model documentation in one clear revision guide.
Learning made visible.
This collection includes eight notes for The Building Blocks of AI, seven for AI Security Threats, and six for AI Models & Data. Each note brings together plain-English explanations, examples, and sources.
First documented on . Last expanded on .
How this notebook grows
New topics bring more explanations, examples, diagrams, and sources to the notebook.
Original learning notes by PromptExploit, with links to TryHackMe and additional references. This independent portfolio is not an official TryHackMe certificate.
AI Models & Data · 8 October 2026
Ramesh reported finishing the room and supplied this shared achievement link. Six notes cover tasks 1–5 and 7, with original visual guides. Task 6 Practical is omitted from the published notes.
Room notes expanded · 23 September 2026
Added AI-Enhanced Attacks, Defensive AI, Securing AI, Practical, and Conclusion. This brought the notebook to fifteen task notes, including the ten supplied practical questions with explained answers and three new visual guides.
First study entry · 18 September 2026
Eight task notes for The Building Blocks of AI. Two task notes for AI Security Threats. Ten notes published.

