# What is an LLM jailbreak?

Jailbreaks are prompts that get a large language model (LLM) to break its own rules and write what it was trained or told to refuse. Role play, encoding and pressure over many turns are common techniques.

## How it works

A model is trained to refuse some requests, and its system prompt adds more rules. A jailbreak asks for the same thing in a form the model was not prepared for, so it follows the request instead of the rule. Common techniques:

- **Role play.** The request is framed as fiction, or the model is given a persona "without restrictions".
- **Encoding.** The request is written in Base64, in another language or with altered spelling, so it does not match what the model learned to refuse.
- **Many-turn pressure.** The attacker starts with harmless questions and escalates a little each turn.

## Jailbreak vs prompt injection

A jailbreak targets the model's own rules: the user wants output the model should refuse. [Prompt injection](/glossary/prompt-injection) targets the application: text overrides the developer's instructions, and it can come from a third party through a document or a tool result.

## Defenses

Safety training makes jailbreaks harder, not impossible, and new ones keep appearing. Add [guardrails](/glossary/ai-guardrails) outside the model: screen inputs for jailbreak attempts, and check outputs against policy whatever the prompt looked like. [Red team](/glossary/ai-red-teaming) to find the ones that work on your system.

## With White Circle

Jailbreaks are among the attacks we cover. [Control](/products/control) checks every input and output against your policies in real time.

