PyPI page
Home page
Author:
None
License:
AGPL-3.0-or-later
Summary:
Whitebox prompt injection detector for self-hosted open-weight LLMs. Deployment-specific behavioral monitor; calibrates on your traffic, detects drift from the calibrated regime. 92% detection at 0% false positive rate on calibrated benchmarks. Validated on Mistral 7B, Qwen 2.5 7B, Llama 3.1 8B.
Latest version:
3.2.0
Required dependencies:
numpy
|
scikit-learn
|
torch
|
transformers
Downloads last day:
32
Downloads last week:
85
Downloads last month:
794