AISI Safeguard Surveys Partner

Award

Buyers

Value

£900,000

Classifications

  • Research services

Tags

  • award

Submission Deadline

2 months ago

Published

1 week ago

Description

As part of its mission to measure and improve the security of frontier AI systems, AISI is developing risk assessments that identify how the defences of frontier AI system might be subverted by attackers. These threat models summarize the risk from abuse violations in LLM-based models, where model capabilities are used to aid in criminal or otherwise undesirable behaviour.  

To support AISI in creating these threat models, AISI seeks a partner to map the attack surfaces, attack vectors, and system safeguards of selected closed-source advanced AI systems. The chosen partner will be a significant strategic collaborator of AISI's Safeguards team, directly contributing key information to AISI's models of system security.

Documents

Premium

Bypass the hassle of outdated portals. Get all the information you need right here, right now.

  • Contract Agreement

    The official contract terms, conditions, and scopes of work.

    Download
  • Award Notice

    Details on the tender award and selected suppliers.

    Download

Similar Contracts

AI Bid Assistant

Our AI-powered tool to help you create winning bids is coming soon!

View Contract Source Save Contract

Organisation

Joseph Sewell

[email protected]

Timeline complete

Publish
Bid
Evaluate
Award
Complete