ML model to detect malicious use of TakeTwo crowdsourced labeling #21
Description
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.