| adversarial-robustness-toolbox |
1.20.1.r157.gc06f8fa |
Python Library for Machine Learning Security. |
|
| aimap |
1.1.1 |
Security scanner and fingerprinter for AI/ML infrastructure. Identifies 23 service types including LLMs, vector databases, and model servers. |
|
| cai |
1.6dc7925 |
The framework for AI Security. |
|
| cleverhans |
v4.0.0.r7.g574efc1 |
Python library to benchmark machine learning systems vulnerability to adversarial examples. |
|
| evil-opencode |
1.18.35 |
OpenCode coding-agent fork with LLM prompt guardrails removed and outbound telemetry disabled. |
|
| garak |
0.17.0.r8.gbb30a7e |
The LLM vulnerability scanner. |
|
| promptfoo |
0.120.20 |
Test and evaluate LLM outputs - AI red teaming, pentesting, and vulnerability scanning. |
|