Securing the Future of AI

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

ASCII Art Prompt Injection is a novel approach to hacking AI assistants. This project leverages the distracting nature of ASCII art to bypass security measures and inject prompts into large language models.

AI Image Data Poisoning demonstrates how to add imperceptible perturbations to images, known as adversarial noise, which can disrupt the training process of AI models.

AI Audio Data Poisoning demonstrates how to add adversarial noise to audio data. This technique, known as audio data poisoning, involves injecting imperceptible noise into audio files to manipulate the behavior of AI systems trained on this data.

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 various applications.

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 threats and attacks.