45 subscribers
התחל במצב לא מקוון עם האפליקציה Player FM !
פודקאסטים ששווה להאזין
בחסות


1 You Can Visit All Seven Continents. But Should You? 26:46
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)
פרקים
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)
54 פרקים
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)
פרקים
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)
54 פרקים
כל הפרקים
×
1 Picking Quantum Resistant Algorithms 14:56

1 Apple Pulls Advanced Data Protection in the UK with Matt Green and Joe Hall 48:30

1 Cryptanalyzing LLMs with Nicholas Carlini 1:20:42

1 Biden’s Cyber-Everything Bagel with Carole House 57:14

1 Quantum Willow with John Schanck and Samuel Jacques 53:36

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 Post-Quantum iMessage with Douglas Stebila 55:34

1 High-assurance Post-Quantum Crypto with Franziskus Kiefer and Karthik Bhargavan 56:13

1 Encrypting Facebook Messenger with Jon Millican and Timothy Buck 59:35

1 Attacking Lattice-based Cryptography with Martin Albrecht 57:20

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

1 'Jerry Solinas deserves a raise' with Steve Weis 57:31

1 Cruel Summer: hybrid signatures, Downfall, Zenbleed, 2G downgrades 58:35

1 Why do we think anything is secure, with Steve Weis 46:17

1 Elon's Encrypted DMs with Matthew Garrett 52:28

1 WhatsApp Key Transparency with Jasleen Malvai and Kevin Lewi 55:43

1 Messaging Layer Security (MLS) with Raphael Robert 55:02


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

1 Has RSA been destroyed by a quantum computer??? 41:16


1 Software Safety and Twitter with Kevin Riggle 58:36
ברוכים הבאים אל Player FM!
Player FM סורק את האינטרנט עבור פודקאסטים באיכות גבוהה בשבילכם כדי שתהנו מהם כרגע. זה יישום הפודקאסט הטוב ביותר והוא עובד על אנדרואיד, iPhone ואינטרנט. הירשמו לסנכרון מנויים במכשירים שונים.