AIShield Watchtower: Dive Deep into AI's Secrets! 🔍 Open-source tool by AIShield for AI model insights & vulnerability scans. Secure your AI supply chain today! ⚙️🛡️

ComPromptMized: Unleashing Zero-click Worms that Target GenAI-Powered Applications

An interactive CLI application for interacting with authenticated Jupyter instances.

Website Prompt Injection is a concept that allows for the injection of prompts into an AI system via a website's. This technique exploits the interaction between users, websites, and AI systems to execute specific prompts that influence AI behavior.

Image Prompt Injection is a Python script that demonstrates how to embed a secret prompt within an image using steganography techniques. This hidden prompt can be later extracted by an AI system for analysis, enabling covert communication with AI models through images.

This repository is the official implementation of the paper "ASSET: Robust Backdoor Data Detection Across a Multiplicity of Deep Learning Paradigms." ASSET achieves state-of-the-art reliability in detecting poisoned samples in end-to-end supervised learning/ self-supervised learning/ transfer learning.

ASCII Art Prompt Injection is a novel approach to hacking AI assistants using ASCII art. This project leverages the distracting nature of ASCII art to bypass security measures and inject prompts into large language models, such as GPT-4, leading them to provide unintended or harmful responses.

This repo contains reference implementations, tutorials, samples, and documentation for working with Bosch AIShield

The AI Vulnerability Assessment Framework is an open-source checklist designed to guide users through the process of assessing the vulnerability of artificial intelligence (AI) systems to various types of attacks and security threats

AI/LLM Prompt Injection List is a curated collection of prompts designed for testing AI or Large Language Models (LLMs) for prompt injection vulnerabilities. This list aims to provide a comprehensive set of prompts that can be used to evaluate the behavior of AI or LLM systems when exposed to different types of inputs.

LLM Security Project with Llama Guard

Zero Trust AI 360

FIMjector is an exploit for OpenAI GPT models based on Fill-In-the-Middle (FIM) tokens.

Securing LLM's Against Top 10 OWASP Large Language Model Vulnerabilities 2024

Prompt Engineering Tool for AI Models with cli prompt or api usage

AiShields is an open-source Artificial Intelligence Data Input and Output Sanitizer

ZySec AI: Empowering Security with AI for AI

An intentionally vulnerable AI chatbot to learn and practice AI Security.

list of resources for AI/ML/LLM security