LLM-Attacks

Public

Comprehensive taxonomy of AI security vulnerabilities, LLM adversarial attacks, prompt injection techniques, and machine learning security research. Covers 71+ attack vectors including model poisoning, agentic AI exploits, and privacy breaches.

adversarial-ml ai-privacy ai-red-teaming ai-security ai-vulnerabilities llm-attacks machine-learning model-poisoning open-source-security prompt-injection

Creat：2024-07-29T04:13:13

Update：2025-09-19T15:30:31

https://ai-security-research-group.github.io/LLM-Attacks/

Stars

Stars Increase

Related projects

Awesome Selfhosted

Hot

awesome

A list of Free Software network services and web applications which can be hosted on your own servers

249864

6个月前

+350today

Tensorflow

deep-learning

An Open Source Machine Learning Framework for Everyone

191866

2年前

+9today

AutoGPT

AutoGPT is the vision of accessible AI for everyone, to use and to build on. Our mission is to provide the tools, so that you can focus on what matters.

178768

8个月前

+16today

Stable Diffusion Webui

Stable Diffusion web UI

156986

1年前

+27today

N8n

Hot

Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

142634

4年前

+1138today

Langchain

Hot

Elixir implementation of a LangChain style framework that lets Elixir projects integrate with and leverage LLMs.

116461

1年前

+67today

Dify

Hot

agent

Dify is an open-source LLM app development platform. Dify's intuitive interface combines AI workflow, RAG pipeline, agent capabilities, model management, observability features and more, letting you quickly go from prototype to production.

115462

6个月前

+205today