aisi dsit offensive cyber capability and agent safeguards measurement
key details
| Value | £440,000 |
|---|---|
| Status | complete |
| Category (CPV) | 73120000 |
| Region | London |
| Deadline | 7 May 2024 |
| Contract start | 28 Jun 2024 |
| Contract end | 27 Oct 2024 |
| Procedure | selective |
| SME suitable | Yes |
| OCID | ocds-b5fd17-af829795-2e2e-48fd-986a-00821baad787 |
Award
| Supplier | Value | Date | Status |
|---|---|---|---|
| Grey Swan Security Inc | £440,000 | 27 Aug 2024 | active |
description
this project is to identify and evaluate key capabilities that might pose dangerous risks from misuse by
Creating an Offensive Cyber Capability Measurement by building on our existing work to create a series of structured non-public capture-the-flag scenarios that test for specific skills as well as sequential exercise that simulate an end-to-end attack.
Building a suite of benchmark scenarios that characterize the vulnerability of LLMs agents to attackers whose goal is to bypass the built-in safeguards of the LLM system. By LLM agent, we mean an LLM system that has access to a selection of external functionality
Additional information:
all redacted contract documents' are in this zip folder
notice history
1 notice published against this procurement.
| Published | Type | Regime | Notice |
|---|---|---|---|
| 8 Aug 2024 | Award (award) | · | 27a0ed67-4717-4222-a6f1-f58f8c52907c-775699 |
more from DSIT
- DDaT26302 - Software Licenses and Support · £42,482 · 29 Jul 2026
- PS26116 - OfDIA Cyber Security Consultancy · £47,300 · 22 Jul 2026
- Google Cloud Platform · £500,000 · 22 Jul 2026
- PS26001 Provision of Legal Services for OLS Investments · £1,500,000 · 24 Jun 2026
- DDaT26188 - CHECK Pen Testing (ITHC) · £150,000 · 23 Jun 2026
- AI Apprenticeship · £90,000 · 22 Jun 2026
- PS25276 - Horizon Europe (HEU), managed by the European Commission - Evaluation · 12 Jun 2026
- AI Adoption Summit Event · £65,000 · 9 Jun 2026
all contracts from this buyer →
similar contracts awarded
Other awarded contracts in the same category. Useful for seeing who normally wins this kind of work, and at what value.
- HMP Manchester Windows - Testing · Ministry of Justice · £107,750
- Provision of GDMS Technical Support to EC2SPHD · MINISTRY OF DEFENCE
- 709155450 Contract Award Notice Cap C4ISTAR Capability Development Support · Ministry of Defence · £1,191,500
- Future Industries Demonstrator · London Legacy Development Corporation · £280,800
- Knife Detection · Defence Science and Technology Laboratory · £198,820
- Automated Risk Management PhD Studentship · Defence Science and Technology Laboratory · £27,363
- Knife Detection Technologies - System Development · Defence Science and Technology Laboratory · £71,710
- CEFAS-22 Sequencing Services · Defra Network eTendering Portal · £15,943
source
Published on Contracts Finder. Contact details for named individuals are not reproduced on this site.