Cryptanalyzing LLMs with Nicholas Carlini

Security Cryptography Whatever

'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)

Chương

1. Mathematical Attacks on AI Security (00:00:00)

2. AI Model Extraction and Security (00:12:07)

3. Model Extraction Security Mechanism Analysis (00:16:11)

4. Model Extraction Attack Methodology Discussion (00:29:18)

5. Training Data Extraction Attack Methodology (00:39:00)

6. Data Poisoning Attacks and Defenses (00:50:59)

7. AI Security Defense Challenges and Strategies (00:59:24)

8. Exploring AI Model Capabilities (01:06:20)

9. Challenges in AI Model Security (01:15:21)