aivillage / llm_verificationLinks
LLM prompt attacks for hacker CTFs via CTFd.
☆13Updated last year
Alternatives and similar repositories for llm_verification
Users that are interested in llm_verification are comparing it to the libraries listed below
Sorting:
- Small tools to assist with using Large Language Models☆11Updated last year
- LLM | Security | Operations in one github repo with good links and pictures.☆57Updated 9 months ago
- ☆30Updated 8 months ago
- https://arxiv.org/abs/2412.02776☆61Updated 9 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆51Updated 10 months ago
- This is a repository to experiment with MCP for security☆43Updated 8 months ago
- Data Scientists Go To Jupyter☆66Updated 7 months ago
- ☆27Updated 2 years ago
- A collection of prompt injection mitigation techniques.☆24Updated 2 years ago
- Open source library for implementing a contextual firewall for LLM based apps.☆12Updated 5 months ago
- 🤖 A GitHub action that leverages fabric patterns through an agent-based approach☆32Updated 8 months ago
- ☆56Updated last week
- 🤖🛡️🔍🔒🔑 Tiny package designed to support red teams and penetration testers in exploiting large language model AI solutions.☆25Updated last year
- A very simple open source implementation of Google's Project Naptime☆169Updated 6 months ago
- using ML models for red teaming☆44Updated 2 years ago
- Secure Jupyter Notebooks and Experimentation Environment☆84Updated 7 months ago
- DEF CON 31 AI Village - LLMs: Loose Lips Multipliers☆10Updated 2 years ago
- Example agents for the Dreadnode platform☆17Updated 2 months ago
- ☆65Updated 2 weeks ago
- Payloads for Attacking Large Language Models☆101Updated 4 months ago
- ☆14Updated last year
- ATLAS tactics, techniques, and case studies data☆80Updated this week
- ☆26Updated 8 months ago
- A ruleset to find potentially malicious code in macOS malware samples☆40Updated 2 years ago
- Code Repository for: AIRTBench: Measuring Autonomous AI Red Teaming Capabilities in Language Models☆77Updated last week
- HoneyAgents is a PoC demo of an AI-driven system that combines honeypots with autonomous AI agents to detect and mitigate cyber threats. …☆56Updated last year
- A command line tool for extracting machine learning ready data from software binaries powered by Radare2☆72Updated 5 months ago
- ☆64Updated 2 months ago
- All things specific to LLM Red Teaming Generative AI☆29Updated 11 months ago
- Code for the paper "Defeating Prompt Injections by Design"☆118Updated 3 months ago