urcuqui/orion
Orion is an AI security framework, inspired by The Art of War, for red and blue teams. It uncovers and mitigates model vulnerabilities with adversarial ML, maps risks to MITRE ATLAS, and offers a Flask web UI to upload models, generate adversarial images, and chat with LLM agents. Use responsibly.
Stars
1
Forks
—
Language
Jupyter Notebook
License
—
Category
Last pushed
Jan 05, 2026
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/llm-tools/urcuqui/orion"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Higher-rated alternatives
KryptSec/oasis
Open-source AI security benchmarking CLI. Measure how AI models perform offensive security tasks...
bobby-tablez/TTP-Threat-Feeds
Threat feeds designed to extract adversarial TTPs and IOCs, using: ✨AI✨
depalmar/ai_for_the_win
Build AI-powered security tools. 50+ hands-on labs covering ML, LLMs, RAG, threat detection,...
format81/TI-Mindmap-GPT
AI-powered tool designed to help producing Threat Intelligence Mindmap.
ethiack/ai4eh
AI for Ethical Hacking - Workshop