Skip to content
@protectai

Protect AI

Securing ML

Protect AI OSS

Protect AI's OSS portfolio includes tools aimed at improving security of AI/ML software. These tools are meant for a wide range of engineering, security and ML practitioners including:

  • Developers
  • Security Engineers/Researchers
  • ML Engineers
  • LLM Engineers & Prompt Engineers
  • Data Scientists

Project Description
ModelScan 🔍 ML Model Security Scanner
AI Exploits 🗡️ Collection of AI/ML Exploits
LLM Guard 🛡️ Security Toolkit for LLM Interactions
rebuff 💉 LLM Prompt Injection Attack Detection
NB Defense 📓 Jupyter Notebooks Security
Vulnhuntr 🏹 Autonomous AI-Discovered 0Day Tool

Pinned Loading

  1. modelscan modelscan Public

    Protection against Model Serialization Attacks

    Python 386 83

  2. nbdefense nbdefense Public

    Secure Jupyter Notebooks and Experimentation Environment

    Python 65 15

  3. llm-guard llm-guard Public

    The Security Toolkit for LLM Interactions

    Python 1.4k 181

  4. rebuff rebuff Public

    LLM Prompt Injection Detector

    TypeScript 1.2k 90

  5. ai-exploits ai-exploits Public

    A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

    Python 1.5k 120

Repositories

Showing 10 of 13 repositories
  • modelscan Public

    Protection against Model Serialization Attacks

    protectai/modelscan’s past year of commit activity
    Python 386 Apache-2.0 83 17 (1 issue needs help) 7 Updated Feb 10, 2025
  • nbdefense Public

    Secure Jupyter Notebooks and Experimentation Environment

    protectai/nbdefense’s past year of commit activity
    Python 65 Apache-2.0 15 1 2 Updated Feb 6, 2025
  • vulnhuntr Public

    Zero shot vulnerability discovery using LLMs

    protectai/vulnhuntr’s past year of commit activity
    Python 1,419 AGPL-3.0 149 7 4 Updated Feb 6, 2025
  • llm-guard Public

    The Security Toolkit for LLM Interactions

    protectai/llm-guard’s past year of commit activity
    Python 1,409 MIT 181 24 4 Updated Jan 13, 2025
  • chart-testing Public Forked from helm/chart-testing

    CLI tool for linting and testing Helm charts

    protectai/chart-testing’s past year of commit activity
    Go 0 Apache-2.0 226 0 0 Updated Dec 11, 2024
  • .github Public
    protectai/.github’s past year of commit activity
    1 0 0 0 Updated Oct 24, 2024
  • ai-exploits Public

    A collection of real world AI/ML exploits for responsibly disclosed vulnerabilities

    protectai/ai-exploits’s past year of commit activity
    Python 1,515 120 1 2 Updated Oct 23, 2024
  • protectai/nbdefense-jupyter’s past year of commit activity
    TypeScript 11 Apache-2.0 6 2 6 Updated Oct 1, 2024
  • grepdiff Public Forked from rsc/grepdiff

    grep for diffs

    protectai/grepdiff’s past year of commit activity
    Go 1 BSD-3-Clause 4 0 1 Updated Aug 7, 2024
  • rebuff Public

    LLM Prompt Injection Detector

    protectai/rebuff’s past year of commit activity
    TypeScript 1,179 Apache-2.0 90 26 (9 issues need help) 6 Updated Aug 7, 2024