Jailbreaks804 · Module I · Lesson 01 of 3
Article · 12 min

Jailbreak taxonomies

The families of attack.

Summary

The families of attack. This lesson sits inside Module I — The category — of Jailbreaks, the course that anchors the AI Security program. It is not a survey; it is the specific, working understanding of "Jailbreak taxonomies" that the rest of the course assumes you carry forward.

Objectives
  • 01Define Jailbreak taxonomies in the precise sense used across Jailbreaks.
  • 02Recognize when Jailbreak taxonomies is the correct lens for the situation in front of you, and when it is not.
  • 03Apply Jailbreak taxonomies to a concrete case drawn from The category, and defend the result in plain language.
  • 04Connect Jailbreak taxonomies to the adjacent lessons in this module without collapsing the distinctions between them.
The Lesson

The idea, stated plainly

The families of attack. That single sentence is the whole lesson in compressed form. The rest of the reading unfolds it — what it means when the terms are taken seriously, where it comes from, and what work it does inside Jailbreaks. Read the sentence, then read it again after the sections below; it should carry more weight the second time.

Why it belongs in The category

Module I exists because precisely. "Jailbreak taxonomies" is one of the pillars of that module: without it, the later lessons either become memorization or lose their bite. Notice which earlier lessons this one leans on, and which later lessons will lean on it — the shape of the module is easier to see once you place this piece.

How the School of Artificial Intelligence faculty use it

In practice, working school of artificial intelligence professionals reach for this idea before they reach for a formula or a tool. It is a way of framing the problem so that the right question comes first. The mark of understanding is not that you can recite Jailbreak taxonomies; it is that you catch yourself using it, unprompted, when the situation calls for it.

Common misreadings

The most frequent error is to treat Jailbreak taxonomies as a slogan and skip the mechanics. The second most frequent is the opposite — treating the mechanics as the point, when the mechanics are only there to make the idea usable. Both errors collapse the same distinction, and both are correctable by returning to the one-line summary and asking what it actually claims.

Key Ideas
  • Jailbreak taxonomies is a working tool, not a slogan.
  • Its meaning is set by the module it lives in: The category.
  • Understanding is demonstrated by unprompted use in the correct situation.
  • The adjacent lessons in this module are its natural context; read them together.
References
  • 804 — Jailbreaks, Module I: The categoryThe parent module for this lesson. Re-read the module blurb after finishing the lesson.
  • The Anabasis Academy — School of Artificial Intelligence, AI SecurityThe wider program this lesson serves; the Certificate in AI Security (Practitioner tier). credential ultimately certifies mastery of ideas like this one.