Salvato in:
| Autori principali: | , , , , , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2505.03742 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866908352227835904 |
|---|---|
| author | O'Gara, Aidan Kulp, Gabriel Hodgkins, Will Petrie, James Immler, Vincent Aysu, Aydin Basu, Kanad Bhasin, Shivam Picek, Stjepan Srivastava, Ankur |
| author_facet | O'Gara, Aidan Kulp, Gabriel Hodgkins, Will Petrie, James Immler, Vincent Aysu, Aydin Basu, Kanad Bhasin, Shivam Picek, Stjepan Srivastava, Ankur |
| contents | Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also pose risks of misuse. Hardware-enabled mechanisms (HEMs) can support responsible AI development by enabling verifiable reporting of key properties of AI training activities such as quantity of compute used, training cluster configuration or location, as well as policy enforcement. Such tools can promote transparency and improve security, while addressing privacy and intellectual property concerns. Based on insights from an interdisciplinary workshop, we identify open questions regarding potential implementation approaches, emphasizing the need for further research to ensure robust, scalable solutions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2505_03742 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Hardware-Enabled Mechanisms for Verifying Responsible AI Development O'Gara, Aidan Kulp, Gabriel Hodgkins, Will Petrie, James Immler, Vincent Aysu, Aydin Basu, Kanad Bhasin, Shivam Picek, Stjepan Srivastava, Ankur Cryptography and Security Advancements in AI capabilities, driven in large part by scaling up computing resources used for AI training, have created opportunities to address major global challenges but also pose risks of misuse. Hardware-enabled mechanisms (HEMs) can support responsible AI development by enabling verifiable reporting of key properties of AI training activities such as quantity of compute used, training cluster configuration or location, as well as policy enforcement. Such tools can promote transparency and improve security, while addressing privacy and intellectual property concerns. Based on insights from an interdisciplinary workshop, we identify open questions regarding potential implementation approaches, emphasizing the need for further research to ensure robust, scalable solutions. |
| title | Hardware-Enabled Mechanisms for Verifying Responsible AI Development |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2505.03742 |