An Early Categorization of Prompt Injection Attacks on Large Language Models

Large language models and AI chatbots have been at the forefront of democratizing artificial intelligence. However, the releases of ChatGPT and other similar tools have been followed by growing concerns regarding the difficulty of controlling large language models and their outputs. Currently, we are witnessing a cat-and-mouse game where users attempt to misuse the models with a novel attack called prompt injections. In contrast, the developers attempt to discover the vulnerabilities and block the attacks simultaneously. In this paper, we …

ai chatbots artificial artificial intelligence attacks cat chatbots chatgpt cs.cl cs.cr cs.lg democratizing game injection injection attacks intelligence language language models large mouse prompt prompt injection prompt injection attacks releases tools