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.
☆179Updated 4 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:
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆203Updated last year
- Lightweight LLM Interaction Framework☆313Updated this week
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆123Updated 7 months ago
- Use LLMs for document ranking☆145Updated 3 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆48Updated 8 months ago
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆76Updated 2 months ago
- This repository contains various attack against Large Language Models.☆112Updated last year
- Code snippets to reproduce MCP tool poisoning attacks.☆164Updated 3 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆49Updated 9 months ago
- ☆44Updated this week
- Repo with random useful scripts, utilities, prompts and stuff☆140Updated last week
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆75Updated 3 months ago
- A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection☆261Updated 3 months ago
- https://arxiv.org/abs/2412.02776☆59Updated 8 months ago
- A powerful tool for automated LLM fuzzing. It is designed to help developers and security researchers identify and mitigate potential jai…☆672Updated 3 weeks ago
- Dropbox LLM Security research code and results☆232Updated last year
- A sandbox environment designed for loading, running and profiling a wide range of files, including machine learning models, ELFs, Pickle,…☆325Updated this week
- DeepTeam is a framework to red team LLMs and LLM systems.☆587Updated this week
- A very simple open source implementation of Google's Project Naptime☆161Updated 4 months ago
- Artefacts for blog post on finding CVE-2025-37899 with o3☆319Updated 2 months ago
- Red-Teaming Language Models with DSPy☆203Updated 5 months ago
- Top 10 for Agentic AI (AI Agent Security) serves as the core for OWASP and CSA Red teaming work☆124Updated last month
- ☆130Updated last month
- A utility to inspect, validate, sign and verify machine learning model files.☆57Updated 6 months ago
- ☆15Updated 7 months ago
- My inputs for the LLM Gandalf made by Lakera☆46Updated last year
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆95Updated 3 months ago
- Every practical and proposed defense against prompt injection.☆503Updated 5 months ago
- An AI-powered application that conducts structured interviews to create and maintain detailed personal profiles across various life aspec…☆45Updated 4 months ago
- Using Agents To Automate Pentesting☆291Updated 6 months ago