SECAI Core · phase 1 of 15
Supervised learning
A category of machine learning that uses labeled data when training algorithms to predict outcomes.
The Explain card
- Plain English
- Supervised learning trains an algorithm on labeled data, where each example already carries the right answer, so the model learns to predict those answers for new inputs.
- Example
- A malware classifier is trained on millions of files, each tagged "malicious" or "benign" by analysts. Later it scores an unknown executable based on what it learned from the tagged ones.
- Why it matters
- The labels are the ground truth the model trusts. Mislabeled or deliberately flipped labels teach the model to wave through exactly the threats you wanted caught.
- Hook
- Learning with an answer key, so guard the answer key.
Where it sits in the deck
Phase 1: What AI Is: Core Concepts and Paradigms
You cannot secure, govern, or attack something you cannot define — establish what AI actually is before any other concept can land.
