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.
☆165Updated last month
Alternatives and similar repositories for llm_backdoor
Users that are interested in llm_backdoor are comparing it to the libraries listed below
Sorting:
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆67Updated 5 months ago
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆109Updated 4 months ago
- A list of curated resources for people interested in AI Red Teaming, Jailbreaking, and Prompt Injection☆134Updated 2 weeks ago
- Codebase of https://arxiv.org/abs/2410.14923☆47Updated 6 months ago
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆202Updated last year
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆46Updated 6 months ago
- Red-Teaming Language Models with DSPy☆192Updated 3 months ago
- Use LLMs for document ranking☆129Updated 3 weeks ago
- Repo with random useful scripts, utilities, prompts and stuff☆98Updated 2 weeks ago
- A sandbox environment designed for loading, running and profiling a wide range of files, including machine learning models, ELFs, Pickle,…☆318Updated this week
- Lightweight LLM Interaction Framework☆267Updated this week
- Top 10 for Agentic AI (AI Agent Security)☆99Updated 2 months ago
- A utility to inspect, validate, sign and verify machine learning model files.☆57Updated 3 months ago
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆71Updated 2 weeks ago
- LLM | Security | Operations in one github repo with good links and pictures.☆29Updated 4 months ago
- Code snippets to reproduce MCP tool poisoning attacks.☆113Updated last month
- ☆100Updated 2 months ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆108Updated last year
- Dropbox LLM Security research code and results☆225Updated 11 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆91Updated last month
- Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER). Fine tuned LLM for penetration testing guidance based on wri…☆22Updated 4 months ago
- A very simple open source implementation of Google's Project Naptime☆142Updated last month
- Every practical and proposed defense against prompt injection.☆456Updated 2 months ago
- ☆40Updated last week
- An OpenAI API Compatible Honeypot Gateway☆16Updated 2 months ago
- Using Agents To Automate Pentesting☆273Updated 3 months ago
- Manual Prompt Injection / Red Teaming Tool☆27Updated 7 months ago
- A MCP server for using Semgrep to scan code for security vulnerabilities.☆148Updated 2 weeks ago
- General research for Dreadnode☆23Updated 10 months ago
- An interactive CLI application for interacting with authenticated Jupyter instances.☆53Updated last week