How can we make it harder to misuse powerful AI systems, such as GPT-4, for propaganda, fraud, academic cheating, copyright violation, and so on? In this talk, I’ll survey one class of approaches, which I’ve called “neurocryptography”: namely, putting cryptographic functionalities inside or on top of AI models. I’ll detail some of the progress we’ve made on making AI outputs detectable as such, with the help of mathematical tools. I’ll also explain the interrelated technical, conceptual, and social challenges in actually deploying these sorts of solutions.
The Mathematics Research Center (MRC) and Stanford Department of Mathematics present Public Lecture "Neurocryptography" given by Scott Aaronson. Scott Aaronson is the David J. Bruton Jr. Centennial Professor of Computer Science at the University of Texas at Austin and the Founding Director of their Quantum Information Center. Professor Aaronson is currently working at OpenAI on the theoretical foundations of AI safety, and his primary area of research is theoretical computer science.
You will need a ticket to gain entry to this event. All tickets are free of charge and available to the general public.
You can find more information about speaker Scott Aaronson here: https://www.scottaaronson.com/