google-research / camel-prompt-injectionLinks
Code for the paper "Defeating Prompt Injections by Design"
☆94Updated 2 months ago
Alternatives and similar repositories for camel-prompt-injection
Users that are interested in camel-prompt-injection are comparing it to the libraries listed below
Sorting:
- A repository of Language Model Vulnerabilities and Exposures (LVEs).☆113Updated last year
- A utility to inspect, validate, sign and verify machine learning model files.☆58Updated 6 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆78Updated 3 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆115Updated last year
- Codebase of https://arxiv.org/abs/2410.14923☆50Updated 10 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆131Updated 8 months ago
- ☆52Updated 2 weeks ago
- Red-Teaming Language Models with DSPy☆212Updated 6 months ago
- ☆59Updated last month
- An interactive CLI application for interacting with authenticated Jupyter instances.☆54Updated 3 months ago
- Lightweight LLM Interaction Framework☆367Updated this week
- Dropbox LLM Security research code and results☆233Updated last year
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆203Updated last year
- A collection of prompt injection mitigation techniques.☆24Updated 2 years ago
- ☆65Updated 7 months ago
- source code for the offsecml framework☆41Updated last year
- Use LLMs for document ranking☆145Updated 4 months ago
- Automated vulnerability discovery and annotation☆67Updated last year
- Multi-agent system (MAS) hijacking demos☆31Updated 3 weeks ago
- ☆142Updated 2 months ago
- Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to pote…☆183Updated 4 months ago
- Example agents for the Dreadnode platform☆16Updated last month
- ☆145Updated 3 months ago
- A benchmark for prompt injection detection systems.☆127Updated last month
- ☆25Updated 2 years ago
- Risks and targets for assessing LLMs & LLM vulnerabilities☆32Updated last year
- Code snippets to reproduce MCP tool poisoning attacks.☆179Updated 4 months ago
- MCP security wrapper☆162Updated last week
- TaskTracker is an approach to detecting task drift in Large Language Models (LLMs) by analysing their internal activations. It provides a…☆64Updated 2 weeks ago
- LLM proxy to observe and debug what your AI agents are doing.☆46Updated last month