ChatGPT Jailbreaks, GPT Assistants Prompt Leaks, GPTs Prompt Injection, LLM Prompt Security, Super Prompts, Prompt Hack, Prompt Security, Ai Prompt Engineering, Adversarial Machine Learning.

The Security Toolkit for LLM Interactions

LLM Prompt Injection Detector

🔍 LangKit: An open-source toolkit for monitoring Large Language Models (LLMs). 📚 Extracts signals from prompts & responses, ensuring safety & security. 🛡️ Features include text quality, relevance metrics, & sentiment analysis. 📊 A comprehensive tool for LLM observability. 👀

Advanced Code and Text Manipulation Prompts for Various LLMs. Suitable for Siri, GPT-4o, Claude, Llama3, Gemini, and other high-performance open-source LLMs.

automatically tests prompt injection attacks on ChatGPT instances

💼 another CV template for your job application, yet powered by Typst and more

Every practical and proposed defense against prompt injection.

⚡ Vigil ⚡ Detect prompt injections, jailbreaks, and other potentially risky Large Language Model (LLM) inputs

Self-hardening firewall for large language models

# Prompt Engineering Hub ⭐️ If you find this helpful, give it a star to show your support! This repository is a one-stop resource for prompt engineering. Also available on: https://promptengineeringhub.dev/

Prompts of GPT-4V & DALL-E3 to full utilize the multi-modal ability. GPT4V Prompts, DALL-E3 Prompts.

Dropbox LLM Security research code and results

This repository provides implementation to formalize and benchmark Prompt Injection attacks and defenses

prompt attack-defense, prompt Injection, reverse engineering notes and examples | 提示词对抗、破解例子与笔记

A benchmark for prompt injection detection systems.

A prompt injection game to collect data for robust ML research

Build production ready apps for GPT using Node.js & TypeScript

My inputs for the LLM Gandalf made by Lakera

This project investigates the security of large language models by performing binary classification of a set of input prompts to discover malicious prompts. Several approaches have been analyzed using classical ML algorithms, a trained LLM model, and a fine-tuned LLM model.