cysecbench/dataset

Generative AI-based CyberSecurity-focused Prompt Dataset for Benchmarking Large Language Models

40
/ 100
Emerging

This project provides a specialized collection of over 12,000 prompts designed to test the security of large language models against cyberattack-related queries. It takes in specific cybersecurity attack scenarios as input and helps evaluate how easily an AI model can be tricked into generating harmful content. Cybersecurity researchers and AI security engineers can use this to benchmark and improve the safety of generative AI systems.

No commits in the last 6 months.

Use this if you need to rigorously test the resilience of an AI model against prompts designed to bypass its safety measures related to cybersecurity threats.

Not ideal if you are looking for a general-purpose dataset for training AI models or for evaluating typical conversational AI performance.

AI security cybersecurity research LLM safety penetration testing AI generative AI security
Stale 6m No Package No Dependents
Maintenance 0 / 25
Adoption 7 / 25
Maturity 16 / 25
Community 17 / 25

How are scores calculated?

Stars

33

Forks

9

Language

Python

License

MIT

Last pushed

Jan 14, 2025

Commits (30d)

0

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/prompt-engineering/cysecbench/dataset"

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