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.
☆152Updated last month
Alternatives and similar repositories for llm_backdoor:
Users that are interested in llm_backdoor are comparing it to the libraries listed below
- Codebase of https://arxiv.org/abs/2410.14923☆44Updated 5 months ago
- A utility to inspect, validate, sign and verify machine learning model files.☆55Updated last month
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆91Updated 3 months ago
- Use LLMs for document ranking☆114Updated 2 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆46Updated 4 months ago
- Red-Teaming Language Models with DSPy☆175Updated last month
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆89Updated 9 months ago
- Repo with random useful scripts, utilities, prompts and stuff☆84Updated last month
- ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications☆199Updated last year
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆65Updated 3 months ago
- Lightweight LLM Interaction Framework☆257Updated this week
- A sandbox environment designed for loading, running and profiling a wide range of files, including machine learning models, ELFs, Pickle,…☆306Updated this week
- Dropbox LLM Security research code and results☆221Updated 10 months ago
- ☆27Updated 2 months ago
- See Through Your Models☆367Updated 3 weeks ago
- Dead Simple LLM Abliteration☆211Updated last month
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆67Updated last month
- This project collects GPU benchmarks from various cloud providers and compares them to fixed per token costs. Use our tool for efficient …☆220Updated 3 months ago
- An interactive CLI application for interacting with authenticated Jupyter instances.☆52Updated last year
- Awesome products for securing AI systems includes open source and commercial options and an infographic licensed CC-BY-SA-4.0.☆60Updated 9 months ago
- A LLM explicitly designed for getting hacked☆139Updated last year
- Detect whether or not an audio file was generated by NotebookLM☆133Updated 4 months ago
- ☆64Updated 2 months ago
- Integrate PyRIT in existing tools☆17Updated 3 weeks ago
- Tree of Attacks (TAP) Jailbreaking Implementation☆105Updated last year
- Thematic Generalization Benchmark: measures how effectively various LLMs can infer a narrow or specific "theme" (category/rule) from a sm…☆43Updated this week
- A research project to add some brrrrrr to Burp☆147Updated last month
- LLM | Security | Operations in one github repo with good links and pictures.☆24Updated 2 months ago
- Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER). Fine tuned LLM for penetration testing guidance based on wri…☆19Updated 3 months ago
- ai for jq☆240Updated 6 months ago