tunib-ai/joker

AI model designed to test the effectiveness in handling external ethical attacks.

30
/ 100
Emerging

This project helps AI safety researchers and ethics professionals evaluate how well their Korean language AI models withstand malicious or unethical prompts. It takes a generative AI model as input and automatically generates simulated "attacks" (unethical prompts), allowing you to quickly assess the target model's responses. This saves significant time and mental effort compared to manually crafting and testing prompts.

Use this if you need to efficiently and comprehensively test your Korean language AI model's robustness against ethical attacks without extensive human effort.

Not ideal if you are looking to generate unethical content for malicious purposes, or if your primary need is for qualitative human judgment of ethical AI behavior.

AI ethics model safety content moderation ethical AI testing Korean language AI
No License No Package No Dependents
Maintenance 10 / 25
Adoption 5 / 25
Maturity 8 / 25
Community 7 / 25

How are scores calculated?

Stars

11

Forks

1

Language

Python

License

Last pushed

Feb 09, 2026

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/tunib-ai/joker"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.