Scalable oversight asks how a weak verifier can check the outputs of computations performed by more powerful AI systems. One proposed approach uses relativizing interactive proofs, in which a weak verifier checks the output of a complex oracle-aided computation by interacting with one or more powerful provers. A promin...
Zi-Yi Guan, Y. Kalai, Ron D. Rothblum et al.· 0 citations
We show that assuming the existence of homomorphic encryption, parallel repetition of all interactive arguments (after being run under homomorphic encryption) reduces the soundness error at a tight exponential rate even in the post-quantum setting. Moreover, we generalize this result to hold for threshold verifiers, wh...
Zvika Brakerski, Andrew Huang, Y. Kalai et al.· arXiv.org· 0 citations
A classical-communication protocol and simulation technique that allows adapting purification-based security arguments for BB84-style states which are prepared through classical interaction to be made available in a hybrid experiment despite the classical transcript uniquely determining the prepared state in a real exe...
Y. Kalai, Justin Raizes· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.