Tavondo
CompetitionsEventsGuidesPlatforms
中文Start matching
CompetitionsEventsGuidesPlatforms
中文Sign in
Tavondo

Find AI competitions and events worth your time.

CompetitionsEventsGuidesPlatforms
Sign inRegisterStart matching

© 2026 Tavondo

中文
  1. Home
  2. Competitions
  3. XGuard护栏揭榜赛
ModelScopeLLMIntermediateRegistration closed

XGuard护栏揭榜赛

A intermediate llm competition requiring roughly 10–30 hours for an end-to-end practice run.

Difficulty
Intermediate
Estimated effort
10–30 hours
Registration deadline
May 25, 2026
Compute
Free GPU OK
OverviewPreparationSource

Overview

Who this competition fits

适合想参与 AI 安全的学生、在职人员或科研人员。技术路线尤其适合有大语言模型训练、数据扩充和开源模型使用经验的人;也有面向技术博主、创意开发者的评测传播与二次开发支线。

Read the original official blurb
XGuard护栏揭榜赛是【大模型安全撬壳计划】系列赛事之一。由阿里巴巴集团安全部主办、致力于为广大AI安全爱好者与开发者提供一个开放协作的创意舞台,通过持续的模型测评、衍生二创与安全加固,推动 “XGuard护栏”进入越用越强、越用越广的良性发展轨道。 Official category: llm. Participants: 333. Organizers: 阿里安全, AAIG.

Preparation

From registration to a first submission

  1. 01

    大语言模型微调

  2. 02

    安全护栏模型训练

  3. 03

    训练数据扩充

  4. 04

    开源模型使用

  5. 05

    模型评测报告撰写

  6. 06

    开源项目二次开发

Before you commit: 主赛道的核心投入在于训练并提交自己的安全护栏模型,同时要在允许扩充数据、且所用开源模型限于 10B 及以下的条件下完成方案。非训练路线则需要产出可发布的深度评测内容,或做出能获得下载量、Star 的衍生项目。

Source

How this page was assembled

Competition information is structured from the official page. Scores are platform estimates for decision support; official rules take precedence.

Official competition page
ModelScope
Last checked
Mar 24, 2026

Entry assessment

est.
55

Prepare before joining

Overall fit estimate

Beginner fit55/100
Learning value58/100

Confirm eligibility and time commitment before moving into formal preparation.

Entry eligibility needs official confirmation

Open official pageSign in to saveOpen guide

Timeline

Registration opens
Mar 24, 2026
Registration deadline
May 25, 2026

Data and review state

Separate what is confirmed from what still needs review. Official rules and deadlines win.

View data stateClose
Source page verifiedMetric confirmedReviewed
Source published
Mar 24, 2026
Published on this site
Aug 11, 2026

Official metric is not published on the ModelScope competition listing; verify scoring on the competition page.

reward_value_usd is a rough CNY→USD estimate (×0.14) for ranking only; use reward_summary for the official prize text.