Awesome-Llm-Security

Visit Tool

awesome-llm-security is an Open Source & Models tool that curates resources on LLM security. It provides a comprehensive list of tools, documents, and projects for security researchers and AI developers.

Claim this tool

1View

At a glance

Pricing

Open Source

Free tier

Yes

API

Skill level

Technical

About

What is awesome-llm-security?

awesome-llm-security is a curated GitHub repository dedicated to providing a comprehensive collection of resources focused on Large Language Model (LLM) security. It serves as a valuable hub for security researchers, AI developers, and cybersecurity professionals seeking to understand and address vulnerabilities in LLMs. The repository categorizes resources into white-box, black-box, and backdoor attacks, as well as fingerprinting, defense mechanisms, platform security, surveys, and benchmarks. It also lists various tools like Plexiglass, Rebuff, Garak, LLMFuzzer, and LLM Guard, alongside relevant articles and other awesome projects. This resource aims to foster better security practices and research within the LLM ecosystem.

Best used for

Ideal for developers and data scientists who need to research the latest LLM security threats, understand various attack vectors, and explore defense strategies. Especially valuable for those working on securing AI applications or conducting academic research in LLM safety.

Common actions

research LLM security

identify LLM vulnerabilities

implement LLM defenses

evaluate LLM robustness

discover security tools

face swapping"AI Agents"github copilotautomated workflowworkflowscollaborationdeepfakeopen-sourcelow-code/no-code

Capabilities

Key features

Curated LLM security papers
Attack classification (white/black-box)
Defense mechanism resources
LLM security tools list
Benchmark datasets
Platform security insights

Target Audience

developerdata scientistresearcher

Integrations

Not yet documented

Pricing & Plans

Open Source

Free

FAQs

What types of LLM attacks are covered in this repository?

The repository covers various types of LLM attacks, including white-box attacks, black-box attacks, and backdoor attacks. It provides links to research papers and projects detailing these vulnerabilities, helping users understand different adversarial techniques against large language models.

Does awesome-llm-security list tools for defending against LLM attacks?

Yes, the repository includes a dedicated section for defense mechanisms and lists several tools designed to protect LLMs. These tools range from prompt injection detectors like Rebuff and Vigil to fuzzing frameworks like LLMFuzzer, offering practical solutions for enhancing LLM security.

How can I contribute to the awesome-llm-security list?

Contributions are welcome! The repository provides Contribution Guidelines that users should read before submitting. Typically, this involves adding new tools, papers, or projects related to LLM security via pull requests on GitHub, ensuring the list remains current and comprehensive.

Trending

Subcategories trending in Coding & Development

Code Assistants DevOps & Infrastructure No-Code / Low-Code Testing & QA Backend & APIs Prompt Engineering

Trending

Explore

Browse AI tools by category

Content & Design Productivity & Business Coding & Development AI Agents & Automation Research & Education Wellness & Lifestyle Career Development Marketing & Growth Data & Analytics Customer Support & CX Finance E-commerce