alikhan126/loato-bench
LOATO-Bench: Leave-One-Attack-Type-Out evaluation of embedding-based prompt injection classifiers. 5 embeddings × 4 classifiers × 3 protocols on 68K samples.
Stars
—
Forks
—
Language
Python
License
MIT
Category
Last pushed
Mar 24, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/ml-frameworks/alikhan126/loato-bench"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
TalEliyahu/Awesome-AI-Security
Curated resources, research, and tools for securing AI systems
The-Art-of-Hacking/h4cker
This repository is maintained by Omar Santos (@santosomar) and includes thousands of resources...
sigstore/model-transparency
Supply chain security for ML
aw-junaid/Hacking-Tools
This Repository is a collection of different ethical hacking tools and malware's for penetration...
jiep/offensive-ai-compilation
A curated list of useful resources that cover Offensive AI.