sshh12 / llm_backdoorLinks
Experimental tools to backdoor large language models by re-writing their system prompts at a raw parameter level. This allows you to potentially execute offline remote code execution without running any actual code on the victim's machine or thwart LLM-based fraud/moderation systems.
☆172Updated 2 months ago
Alternatives and similar repositories for llm_backdoor
Users that are interested in llm_backdoor are comparing it to the libraries listed below
Sorting:
- A utility to inspect, validate, sign and verify machine learning model files.☆57Updated 4 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆48Updated 8 months ago
- A sandbox environment designed for loading, running and profiling a wide range of files, including machine learning models, ELFs, Pickle,…☆322Updated last week
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆120Updated 6 months ago
- A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection☆195Updated last month
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆69Updated last month
- This repository contains various attack against Large Language Models.☆107Updated last year
- A MCP server for using Semgrep to scan code for security vulnerabilities.☆200Updated last week
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆203Updated last year
- Red-Teaming Language Models with DSPy☆198Updated 4 months ago
- Lightweight LLM Interaction Framework☆285Updated this week
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆46Updated 7 months ago
- Using Agents To Automate Pentesting☆278Updated 5 months ago
- A very simple open source implementation of Google's Project Naptime☆155Updated 3 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆73Updated last month
- Repo with random useful scripts, utilities, prompts and stuff☆107Updated 2 weeks ago
- Dropbox LLM Security research code and results☆227Updated last year
- Use LLMs for document ranking☆136Updated 2 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆91Updated 2 months ago
- XBOW Validation Benchmarks☆104Updated last week
- ☆112Updated 2 weeks ago
- A benchmark for prompt injection detection systems.☆118Updated last month
- ☆51Updated last week
- ⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs☆394Updated last year
- Every practical and proposed defense against prompt injection.☆485Updated 4 months ago
- The LLM Red Teaming Framework☆452Updated last week
- ☆68Updated last week
- A research project to add some brrrrrr to Burp☆178Updated 4 months ago
- https://arxiv.org/abs/2412.02776☆57Updated 6 months ago
- An OpenAI API Compatible Honeypot Gateway☆16Updated 3 months ago