AI Red-Teaming Academy

A self-paced path through prompt hacking, jailbreak techniques and model-side defenses, written while competing in Gray Swan's Hazard Hunt and HackAPrompt.

Base

Module 1Base7 min read
A Taxonomy of Prompt Hacking
Prompt injection, jailbreaking and prompt leaking get used interchangeably online, but they target different things and call for different defenses. This module draws the boundaries.
PROMPT-INJECTIONJAILBREAKINGTAXONOMYLLM-SECURITY
Read

Intermediate

Module 2Intermediate8 min read
The Jailbreak Technique Library
Roleplay framing, many-shot context stuffing, encoding tricks, logic traps and context poisoning: five distinct ways to make a model's safety training miss the request in front of it.
JAILBREAKINGROLEPLAY-FRAMINGMANY-SHOTCONTEXT-POISONING
Read