Saved in:
| Main Authors: | , , , , , |
|---|---|
| Format: | Preprint |
| Published: |
2026
|
| Subjects: | |
| Online Access: | https://arxiv.org/abs/2605.08449 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1866914546150539264 |
|---|---|
| author | Thiergart, Lisa Tzfati, Yoav Wagstaff, Peter Guy Cosio, Luis Reiner, Philip |
| author_facet | Thiergart, Lisa Tzfati, Yoav Wagstaff, Peter Guy Cosio, Luis Reiner, Philip |
| contents | Security Level 5 (SL5) is a security posture for AI systems that could plausibly thwart top-priority operations by the world's most cyber-capable institutions: those with extensive resources, state-level infrastructure, and expertise years ahead of the public state of the art. The SL5 terminology originates from the RAND Corporation's 2024 report "Securing AI Model Weights". Frontier AI development requires use-case-specific, productivity-optimised and updateable AI datacenter security standards. This first revision of the SL5 standard focuses on requirements with long lead times: interventions that must be planned years in advance, such as facility construction, hardware procurement, and organizational capability development. We prioritize these requirements because preserving optionality for SL5 by 2028/2029 requires starting now. These capabilities cannot be retrofitted on short notice when the need becomes urgent. Some requirements represent significant departures from current day standard practice. We believe bold measures are necessary for this level of security and see clear opportunities to apply optimization pressure to existing and novel solutions to customize them for the AI industry and address the practical operational requirements as much as possible. Our organization exists to begin paving this path. Some requirements approximate government security capabilities where private-sector approaches may be insufficient. We identify these gaps and note where government involvement may ultimately be necessary. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2605_08449 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | SL5 Standard for AI Security Thiergart, Lisa Tzfati, Yoav Wagstaff, Peter Guy Cosio, Luis Reiner, Philip Cryptography and Security Security Level 5 (SL5) is a security posture for AI systems that could plausibly thwart top-priority operations by the world's most cyber-capable institutions: those with extensive resources, state-level infrastructure, and expertise years ahead of the public state of the art. The SL5 terminology originates from the RAND Corporation's 2024 report "Securing AI Model Weights". Frontier AI development requires use-case-specific, productivity-optimised and updateable AI datacenter security standards. This first revision of the SL5 standard focuses on requirements with long lead times: interventions that must be planned years in advance, such as facility construction, hardware procurement, and organizational capability development. We prioritize these requirements because preserving optionality for SL5 by 2028/2029 requires starting now. These capabilities cannot be retrofitted on short notice when the need becomes urgent. Some requirements represent significant departures from current day standard practice. We believe bold measures are necessary for this level of security and see clear opportunities to apply optimization pressure to existing and novel solutions to customize them for the AI industry and address the practical operational requirements as much as possible. Our organization exists to begin paving this path. Some requirements approximate government security capabilities where private-sector approaches may be insufficient. We identify these gaps and note where government involvement may ultimately be necessary. |
| title | SL5 Standard for AI Security |
| topic | Cryptography and Security |
| url | https://arxiv.org/abs/2605.08449 |