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
Securitycorca-ai
awesome-llm-security
A curated list of tools, papers and projects on LLM security: white-box and black-box attacks, backdoors, defense, platform security. A handy starting point for surveying the field.
Who it is for
For people studying LLM security who want papers and tools by topic.
How to start
- Open the README table of contents and pick a topic such as Defense or Platform Security
- Start with the Survey section for the big picture
- Follow the links to papers and tools on that topic
Steps are taken from the README. Check the current version in the repository before running them.
Stars over the last 30 days
+18Sep 6 — Oct 6
Author's description
A curation of awesome tools, documents and projects about LLM Security.
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.