sshh12 / llm_backdoor
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.
☆158Updated 3 weeks ago
Alternatives and similar repositories for llm_backdoor:
Users that are interested in llm_backdoor are comparing it to the libraries listed below
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆67Updated 4 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆106Updated 4 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆46Updated 6 months ago
- Red-Teaming Language Models with DSPy☆183Updated 2 months ago
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆201Updated last year
- A utility to inspect, validate, sign and verify machine learning model files.☆56Updated 2 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆69Updated 2 weeks ago
- Repo with random useful scripts, utilities, prompts and stuff☆93Updated 2 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆46Updated 5 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆89Updated last week
- ☆34Updated 2 months ago
- ☆64Updated 3 months ago
- A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection☆101Updated last week
- A sandbox environment designed for loading, running and profiling a wide range of files, including machine learning models, ELFs, Pickle,…☆311Updated this week
- Top 10 for Agentic AI (AI Agent Security) - Pre-release version☆84Updated last month
- ☆31Updated this week
- An interactive CLI application for interacting with authenticated Jupyter instances.☆53Updated last year
- Using Agents To Automate Pentesting☆264Updated 3 months ago
- A steganography tool for automatically encoding images that act as prompt injections/jailbreaks for AIs with code interpreter and vision.☆80Updated 6 months ago
- A very simple open source implementation of Google's Project Naptime☆141Updated 3 weeks ago
- Code scanner to check for issues in prompts and LLM calls☆61Updated 2 weeks ago
- A MCP server for using Semgrep to scan code for security vulnerabilities.☆127Updated 2 weeks ago
- Applying the ideas of Deepseek R1 to computer use☆211Updated 2 months ago
- A security scanning tool for MCP servers☆457Updated last week
- ☆33Updated 6 months ago
- General research for Dreadnode☆21Updated 10 months ago
- Code release for Best-of-N Jailbreaking☆480Updated 2 months ago
- MCP server for querying the Shodan API☆32Updated last month
- This repository contains various attack against Large Language Models.☆104Updated 11 months ago
- A better way of testing, inspecting, and analyzing AI Agent traces.☆35Updated last week