What Can the Theory of Cryptography Tell Us About AI Verification?
Applies interactive proof systems, cryptographic watermarking, and worst-case adversarial guarantees to verifiable machine learning.
Turing Award Laureate & Director of the Simons Institute
Self-contained public lectures, keynote addresses, and research seminars.
Applies interactive proof systems, cryptographic watermarking, and worst-case adversarial guarantees to verifiable machine learning.



Discrete proof invariants, stochastic conditioning, pseudorandomness, and P vs. NP
MIT · Harvard University · UCLA +2