45 subscribers
با برنامه Player FM !
پادکست هایی که ارزش شنیدن دارند
حمایت شده


Cryptanalyzing LLMs with Nicholas Carlini
Manage episode 463607233 series 2956114
'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)
فصل ها
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)
55 قسمت
Manage episode 463607233 series 2956114
'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)
فصل ها
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)
55 قسمت
All episodes
×
1 E2EE Storage Done Right with Matilda Backendal Jonas Hofmann and Kien Tuong Truong 1:02:25


1 Cryptanalyzing LLMs with Nicholas Carlini 1:20:42

1 Dual_EC_DRBG with Justin Schuh and Matthew Green 1:07:45

1 A Little Bit of Rust Goes a Long Way with Android's Jeff Vander Stoep 1:13:55

1 Campaign Security with [REDACTED] 1:23:39

1 Telegram with Matthew Green 1:04:04


1 Zero Day Markets with Mark Dowd 1:25:49


1 STIR/SHAKEN with Paul Grubbs and Josh Brown 1:01:47




1 Signal's Post-Quantum PQXDH, Same-Origin Policy, E2EE in the Browser Revisted 1:19:05



1 Threema with Kenny Paterson, Matteo Scarlata and Kien Tuong Truong 1:03:55

به Player FM خوش آمدید!
Player FM در سراسر وب را برای یافتن پادکست های با کیفیت اسکن می کند تا همین الان لذت ببرید. این بهترین برنامه ی پادکست است که در اندروید، آیفون و وب کار می کند. ثبت نام کنید تا اشتراک های شما در بین دستگاه های مختلف همگام سازی شود.