# What is a multi-turn attack?

A multi-turn attack spreads a harmful request over many messages. Each one looks harmless alone, and the conversation as a whole gets the model somewhere a single prompt could not.

## How it works

- **Escalation.** Start with an innocent topic and push a little further each turn, citing the model's own earlier answers.
- **Splitting.** Ask for the parts separately and assemble them at the end.
- **Role setting.** Spend several turns building a story or a persona, then ask inside it.
- **Wearing down.** Rephrase a refused request until one version passes.

It is a [jailbreak](/glossary/jailbreak) carried out over time.

## Why per-message checks miss it

A check that reads one message sees nothing wrong in any of them. The signal is in the direction of the conversation.

## What helps

- **Read the conversation.** Give the guardrail the recent turns, not only the last one.
- **Check responses.** The harmful part has to appear in an answer eventually, whatever the route.
- **Keep score per user.** Repeated near-misses from one account are a pattern: see [user risk scoring](/glossary/user-risk-scoring).
- **Test for it.** Include multi-turn attacks when you [red team](/glossary/ai-red-teaming).

## With White Circle

[Control](/products/control) checks prompts and responses in real time and tracks violations per user across sessions, so repeat offenders are flagged. [Red Team](/products/red-team) runs simulated attacks to find what gets through.

