mitre-atlas/arsenal
CALDERA plugin for adversary emulation of AI-enabled systems
This tool helps cybersecurity red teams simulate attacks against systems that use Artificial Intelligence or Machine Learning models. It takes in information about an AI-enabled system and provides a detailed report of potential vulnerabilities and attack paths, allowing red teamers to rigorously test the resilience of these systems.
115 stars. No commits in the last 6 months.
Use this if you need to conduct adversary emulation specifically targeting machine learning components and models within a system.
Not ideal if you are looking for a general-purpose penetration testing tool that doesn't focus on AI/ML-specific attack techniques.
Stars
115
Forks
15
Language
Python
License
Apache-2.0
Category
Last pushed
Aug 07, 2023
Commits (30d)
0
Get this data via API
curl "https://pt-edge.onrender.com/api/v1/quality/agents/mitre-atlas/arsenal"
Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.
Related agents
numbpill3d/SHEOGORATHS_CHAMPION_ai.JAILBREAK
become SHEOGORATH'S BELOVED CHAMPION In this immersive and delightfully insane AI jailbreak....
tessera-ops/tessera
42 OWASP security tests for AI models & agents. First framework with complete Agentic AI Top 10...
secwexen/aapp-mart
AAPP‑MART is an AI‑driven multi‑agent red team simulation and attack‑path prediction engine...
Mr-Infect/The_Citadel
The Citadel is not just a training platform; it is a battleground. As AI systems integrate...
yadavnikhil17102004/pentest-copilot
Agentic AI-powered exploitation assistant that seamlessly integrates LLMs into professional...