Call-for-Code-for-Racial-Justice / Call-for-Code-for-Racial-Justice/TakeTwo-DataScience

ML model to detect malicious use of TakeTwo crowdsourced labeling

未关闭
#21 3 条评论 0 个 reaction 已指派 0 人 在 GitHub 查看
design-thinking idea Machine Learning stale
主要语言
Jupyter Notebook
星标
8
派生
8
PR 合并指标
30 天内没有已合并 PR

描述

### Background on the problem the feature will solve/improved user experience
As an open-source, data crowdsourced solution, there is potential for malicious use/contributions

### Describe the solution you'd like
Develop an ML model(s) that detects malicious use such as:
- seeking to spam
- alter what is considered by racist, by making offensive racist terms seem less racist or identifying non-racist, benign terms as racist with the intent of making the api useless (by classifying everything as racist)
-
### Tasks
Description of the development tasks needed to complete this issue, including tests,

### Acceptance Criteria
Standards we believe this issue must reach to be considered complete and ready for a pull request. E.g precisely all the user should be able to do with this update, performance requirements, security requirements, etc as appropriate.

贡献指南

打开贡献指南

调研方向

未指定任何文件、入口点、测试或验收标准。先调查代码库中的 Jupyter notebooks 和现有 data-science workflow,然后在实现之前定义恶意使用信号、评估数据以及可衡量的完成标准。

由索引模型根据 Issue 内容生成。

评估

技术栈
jupyter-notebook, machine-learning
领域
machine-learning, security
Issue 类型
功能
难度
5/5
预计耗时
一周以上
活跃度
停滞
描述清晰度
需要澄清
新手友好度
15/100

把新 issue 发到你的邮箱

精选适合新手参与的 GitHub issue 摘要。