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.
☆186Updated 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
Sorting:
- Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems☆216Updated last month
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆88Updated 5 months ago
- Lightweight LLM Interaction Framework☆389Updated this week
- Codebase of https://arxiv.org/abs/2410.14923☆51Updated last year
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆142Updated 10 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆52Updated 11 months ago
- This repository contains various attack against Large Language Models.☆115Updated last year
- Use LLMs for document ranking☆151Updated 6 months ago
- Code for the paper "Defeating Prompt Injections by Design"☆138Updated 4 months ago
- ☆45Updated last week
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆78Updated 5 months ago
- Code snippets to reproduce MCP tool poisoning attacks.☆183Updated 6 months ago
- Repo with random useful scripts, utilities, prompts and stuff☆175Updated last week
- https://arxiv.org/abs/2412.02776☆64Updated 10 months ago
- Dropbox LLM Security research code and results☆237Updated last year
- LLM | Security | Operations in one github repo with good links and pictures.☆63Updated 9 months ago
- AI agent for autonomous cyber operations☆319Updated last week
- A utility to inspect, validate, sign and verify machine learning model files.☆59Updated 8 months ago
- Using Agents To Automate Pentesting☆304Updated 9 months ago
- Red-Teaming Language Models with DSPy☆235Updated 8 months ago
- ☆91Updated last week
- A very simple open source implementation of Google's Project Naptime☆172Updated 7 months ago
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agents☆126Updated 3 weeks ago
- All-in-one offensive security toolbox with AI agent and MCP architecture. Integrates tools like Nmap, Metasploit, FFUF, SQLMap. Enables p…☆455Updated 4 months ago
- Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER). Fine tuned LLM for penetration testing guidance based on wri…☆32Updated 10 months ago
- Powerful LLM Query Framework with YAML Prompt Templates. Made for Automation☆33Updated last month
- We present MAPTA, a multi-agent system for autonomous web application security assessment that combines large language model orchestratio…☆69Updated 2 months ago
- Manual Prompt Injection / Red Teaming Tool☆42Updated last year
- A sandbox environment designed for loading, running and profiling a wide range of files, including machine learning models, ELFs, Pickle,…☆331Updated last week
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆97Updated 6 months ago