45 subscribers
使用Player FM应用程序离线!
值得一听的播客
赞助


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)
章节
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集单集
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)
章节
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集单集
所有剧集
×











欢迎使用Player FM
Player FM正在网上搜索高质量的播客,以便您现在享受。它是最好的播客应用程序,适用于安卓、iPhone和网络。注册以跨设备同步订阅。