👑 WE WON! 🎉
LFGGGG! @Rhynorater@0xLupin@monkehack and I won MVH at the Google Live Hacking Event in Tokyo last week! It was focused on their AI products. We also had an awesome time in Japan. I'll post some of the highlights below.
This morning I was hacking the new ChatGPT API and found something super interesting: there are over 80 secret plugins that can be revealed by removing a specific parameter from an API call.
The secret plugins include a "DAN plugin", "Crypto Prices Plugin", and many more.
I'm a hacker and AI researcher who has reported vulnerabilities to OpenAI, Google, and others. I wrote this guide as a reference of all of the ways that you can hack AI.
It has saved me hours. Bookmark this if you need a reference for what all to try (AND includes mitigations).
The most interesting piece of the ChatGPT plugin leak was the plugin that @OpenAI was using to assess the security of the other plugins. Here's how it works.
The first part of the prompt was the instructions:
🚨 Massive AI Security Release 🚨
@NIST just put out the best AI Security Publication that I've ever seen.
It is 106 pages of deep, technical content. It references real-world practical attacks. In this thread is the link and I'm going to cover a few highlights. 👇