Cryptanalyzing LLMs with Nicholas Carlini

0 Anmeldelser
0
Episode
52 of 55
Længde
1T 20M
Sprog
Engelsk
Format
Kategori
Fakta

'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: https://youtu.be/vZ64xPI2Rc0

Transcript: https://securitycryptographywhatever.com/2025/01/28/cryptanalyzing-llms-with-nicholas-carlini/

Links:

- https://nicholas.carlini.com - “Stealing Part of a Production Language Model”: https://arxiv.org/pdf/2403.06634 - ‘Why I attack"’: https://nicholas.carlini.com/writing/2024/why-i-attack.html - “Cryptanalytic Extraction of Neural Network Models”, CRYPTO 2020: https://arxiv.org/abs/2003.04884 - “Stochastic Parrots”: https://dl.acm.org/doi/10.1145/3442188.3445922 - https://help.openai.com/en/articles/5247780-using-logit-bias-to-alter-token-probability-with-the-openai-api - https://community.openai.com/t/temperature-top-p-and-top-k-for-chatbot-responses/295542 - https://opensource.org/license/mit - https://github.com/madler/zlib - https://ai.meta.com/blog/yann-lecun-ai-model-i-jepa/ - https://nicholas.carlini.com/writing/2024/how-i-use-ai.html

"Security Cryptography Whatever" is hosted by Deirdre Connolly (@durumcrustulum), Thomas Ptacek (@tqbf), and David Adrian (@davidcadrian)


Lyt når som helst, hvor som helst

Nyd den ubegrænsede adgang til tusindvis af spændende e- og lydbøger - helt gratis

  • Lyt og læs så meget du har lyst til
  • Opdag et kæmpe bibliotek fyldt med fortællinger
  • Eksklusive titler + Mofibo Originals
  • Opsig når som helst
Prøv nu
DK - Details page - Device banner - 894x1036

Other podcasts you might like ...