
Sign up to save your podcasts
Or
'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)
4.9
7777 ratings
'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)
1,976 Listeners
272 Listeners
365 Listeners
626 Listeners
621 Listeners
176 Listeners
154 Listeners
312 Listeners
408 Listeners
7,879 Listeners
92 Listeners
401 Listeners
127 Listeners
43 Listeners
47 Listeners