Cryptanalyzing LLMs with Nicholas Carlini

'Let us model our large language model as a hash function—' Sold. Our special guest Nicholas Carlini joins us to discuss differential cryptanalysis on LLMs and other attacks, just as the ones that made OpenAI turn off some features, hehehehe. Watch episode on YouTube: Transcript: Links: - - “Stealing Part of a Production Language Model”: - ‘Why I attack"’: - “Cryptanalytic Extraction of Neural Network Models”, CRYPTO 2020: - “Stochastic Parrots”: - - - - - - "Security Cryptography Whatever" is hosted by Deirdre Connolly (@durumcrustulum), Thomas Ptacek (@tqbf), and David Adrian (@dadrian)

You can listen to Cryptanalyzing LLMs with Nicholas Carlini online on Radio and Podcast. Open the player on this page to stream the available audio.

Cryptanalyzing LLMs with Nicholas Carlini is an episode from Security. Cryptography. Whatever. by Deirdre Connolly, Thomas Ptacek, David Adrian.

This episode is 80:42 long.

This episode was published on Jan 28, 2025.

Yes. Use the heart button on the episode page to add it to your favorite episodes list.

Yes. This page shows related episodes from Security. Cryptography. Whatever. when more episodes are available from the podcast feed.