A framework that finds and masks personal data in text, images and tables. It detects the data, then redacts or replaces it so it can be safely sent to a model.
All repositories
Securityprotectai
modelscan
A scanner for model files that detects serialization attacks, such as malicious code inside a pickle. It checks the file before you load it.
Who it is for
For people who download third-party models from hubs and want to avoid running malicious code.
How to start
- Install:
pip install modelscan - Scan a model file:
modelscan -p /path/to/model_file.pkl - Read the report and do not load the model if issues are found
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+10Sep 6 — Sep 28
Author's description
Protection against Model Serialization Attacks
More in «Security»
A vulnerability scanner for LLMs: it runs a model through a set of probes for prompt injection, data leakage, toxicity and other failures. Works as a command-line tool.
A Python framework that checks LLM inputs and outputs with ready validators from Guardrails Hub and helps produce structured answers. It catches risks before a reply reaches the user.
NVIDIA's toolkit for programmable rails in LLM-based conversational systems. Rules live in config and control what the bot talks about and does.
Microsoft's framework for proactively finding risks in generative AI systems. It helps automate red teaming against models and applications.
Meta's generative AI safety project: the Llama Guard and Prompt Guard filter models, the Code Shield scanner and the CyberSec Eval test suites. It pairs defense with attack-based testing.