---
id: "qwen3guard-technical-report"
title: "Qwen3Guard Technical Report"
creator: "Haiquan Zhao and colleagues / Qwen Team"
creator_url: "https://github.com/QwenLM/Qwen3Guard"
creator_x: null
url: "https://arxiv.org/abs/2510.14276v1"
level: "advanced"
level_max: null
category: "security-and-red-teaming"
subcategory: "safety-and-alignment-evals"
region: "CN"
license: "closed"
license_scope: "linked-resource"
access: "free"
models: ["qwen3guard"]
source_date: "2025-10-16"
date_added: "2026-10-18"
---

[Jailbreaking and red teaming](/security-and-red-teaming/index.md)

# Qwen3Guard Technical Report

by [Haiquan Zhao and colleagues / Qwen Team](https://github.com/QwenLM/Qwen3Guard)

[Read the original →](https://arxiv.org/abs/2510.14276v1)

Understand Qwen’s multilingual safety classifiers and the distinction between whole-response and streaming moderation.

The report introduces generative and streaming guardrail models for classifying prompt and response safety. It describes three-way safety judgments and token-level monitoring during generation, rather than a jailbreak attack method.

Level: [Advanced](/levels/index.md#advanced)
Models: qwen3guard
Category: [Jailbreaking and red teaming](/security-and-red-teaming/index.md)
Tags: [primary-source](/tags/primary-source/index.md), [regional-coverage](/tags/regional-coverage/index.md)
Source date: 2025-10-16
Added: 2026-10-18
Last verified: 2026-10-18
Status: ok
Prerequisites: Requires familiarity with model evaluation, safety classifiers and streaming inference.
Subcategory: [safety and alignment evals](/security-and-red-teaming/safety-and-alignment-evals/index.md)
Region: CN
Original language: en
Access: free
Resource reuse: closed: No general open-reuse grant established for the linked resource. Closed is a conservative reuse bucket, not a claim that access is restricted; model licensing does not license a paper. [Facet definitions](/about/index.md#facets)

Summary in our own words. Rights remain with the original creator. [Credit and correction policy](/about/index.md#credit-policy).

[Plain-text Markdown copy](/security-and-red-teaming/safety-and-alignment-evals/qwen3guard-technical-report/index.md)