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.
☆192Updated 2 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:
- Here Comes the AI Worm: Preventing the Propagation of Adversarial Self-Replicating Prompts Within GenAI Ecosystems☆220Updated 3 months ago
- Project Mantis: Hacking Back the AI-Hacker; Prompt Injection as a Defense Against LLM-driven Cyberattacks☆92Updated 6 months ago
- Code snippets to reproduce MCP tool poisoning attacks.☆187Updated 8 months ago
- A Completely Modular LLM Reverse Engineering, Red Teaming, and Vulnerability Research Framework.☆52Updated last year
- A productionized greedy coordinate gradient (GCG) attack tool for large language models (LLMs)☆150Updated 11 months ago
- Code for the paper "Defeating Prompt Injections by Design"☆172Updated 5 months ago
- Codebase of https://arxiv.org/abs/2410.14923☆52Updated last year
- This repository contains various attack against Large Language Models.☆122Updated last year
- Repo with random useful scripts, utilities, prompts and stuff☆189Updated 2 weeks ago
- Use LLMs for document ranking☆159Updated 7 months ago
- Lightweight LLM Interaction Framework☆396Updated this week
- ☆113Updated this week
- AI agent for autonomous cyber operations☆428Updated last week
- LLM | Security | Operations in one github repo with good links and pictures.☆67Updated 11 months ago
- ☆49Updated last week
- A YAML based format for describing tools to LLMs, like man pages but for robots!☆81Updated 7 months ago
- Raptor turns Claude Code into a general-purpose AI offensive/defensive security agent. By using Claude.md and creating rules, sub-agents,…☆433Updated last week
- We present MAPTA, a multi-agent system for autonomous web application security assessment that combines large language model orchestratio…☆81Updated 3 months ago
- Repository for CoSAI Workstream 4, Secure Design Patterns for Agentic Systems☆38Updated this week
- Dropbox LLM Security research code and results☆248Updated last year
- Red-Teaming Language Models with DSPy☆244Updated 9 months ago
- https://arxiv.org/abs/2412.02776☆66Updated last year
- A knowledge source about TTPs used to target GenAI-based systems, copilots and agents☆129Updated 2 months ago
- Cybersecurity Intelligent Pentesting Helper for Ethical Researcher (CIPHER). Fine tuned LLM for penetration testing guidance based on wri…☆34Updated 11 months ago
- A very simple open source implementation of Google's Project Naptime☆175Updated 8 months ago
- Payloads for Attacking Large Language Models☆109Updated 6 months ago
- A subset of jailbreaks automatically discovered by the Haize Labs haizing suite.☆100Updated 7 months ago
- ☆178Updated 5 months ago
- Secure Code Review AI Agent (SeCoRA) - AI SAST☆54Updated 10 months ago
- Make your GenAI Apps Safe & Secure Test & harden your system prompt☆598Updated 2 months ago