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

GPT 2 model trained on fake PII to study PII leakage from large language models

A secure, AI-enhanced file scanning tool built on Flask, strengthened with ClamAV and PDF analysis, designed to vigilantly detect digital threats and potential vulnerabilities.

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.

A curated list of useful resources that cover Offensive AI.