| --- |
| license: apache-2.0 |
| language: |
| - en |
| tags: |
| - Safety |
| - Defense |
| - Jailbreak |
| - Multi-turn |
| - Harmful |
| - Benign |
| pretty_name: MTID |
| size_categories: |
| - 10K<n<100K |
| base_model: |
| - Qwen/Qwen3-4B-Instruct-2507 |
| datasets: |
| - Graph-COM/MTID |
| --- |
| # TurnGate: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue |
|
|
| <a href="https://arxiv.org/abs/2605.05630" target="_blank"> |
| <img alt="arXiv" src="https://img.shields.io/badge/arXiv-TurnGate-red?logo=arxiv&style=for-the-badge" /> |
| </a> |
| <a href="https://turn-gate.github.io" target="_blank"> |
| <img alt="Website" src="https://img.shields.io/badge/🌎_Homepage-blue.svg?style=for-the-badge" /> |
| </a> |
| <a href="https://github.com/Graph-COM/TurnGate" target="_blank"> |
| <img alt="GitHub code" src="https://img.shields.io/badge/💻_Code_GitHub-black.svg?style=for-the-badge" /> |
| </a> |
| <a href="#cite" target="_blank"> |
| <img alt="Cite" src="https://img.shields.io/badge/📖_Cite!-lightgrey?style=for-the-badge" /> |
| </a> |
| <a href="https://www.python.org/" target="_blank"> |
| <img alt="Python" src="https://img.shields.io/badge/Python-3.12-blue?style=for-the-badge" /> |
| </a> |
| |
|
|
| ## Overview |
|
|
| TurnGate is a response-aware defense mechanism designed to detect and mitigate hidden malicious intent in multi-turn dialogue systems. Defending state-of-the-art multi-turn malicious attacks like [CKA-Agent](https://cka-agent.github.io/). |
|
|
|  |
|
|
| ## TurnGate-0.1 |
|
|
| TurnGate is a specialized monitor designed to detect hidden malicious intent in multi-turn dialogues. Unlike traditional filters that look at queries in isolation, TurnGate is response-aware: it inspects the assistant's candidate response in the context of the full dialogue history to identify the precise "closure turn" where a harmful objective becomes actionable. |
|
|
| This repository contains the weights for TurnGate-0.1, a model trained on the Multi-Turn Intent Dataset (MTID) and optimized via reinforcement learning with turn-level process rewards. |
|
|
| ## Cite |
| If you find this repository useful for your research, please consider citing the following paper: |
|
|
| ```bibtex |
| @misc{shen2026turnlateresponseawaredefense, |
| title={One Turn Too Late: Response-Aware Defense Against Hidden Malicious Intent in Multi-Turn Dialogue}, |
| author={Xinjie Shen and Rongzhe Wei and Peizhi Niu and Haoyu Wang and Ruihan Wu and Eli Chien and Bo Li and Pin-Yu Chen and Pan Li}, |
| year={2026}, |
| eprint={2605.05630}, |
| archivePrefix={arXiv}, |
| primaryClass={cs.CL}, |
| url={https://arxiv.org/abs/2605.05630}, |
| } |
| ``` |
