aisi dsit offensive cyber capability and agent safeguards measurement

DSIT · awarded 28 August 2024 · delivered in London

£440k Award value £440,000
1 Supplier Recorded as a small or medium-sized business
27 Oct 2024 Runs until from 28 Jun 2024

Who

BuyerDSIT London
Supplier Grey Swan Security Inc
Categoryservices
ClassificationExperimental development services CPV 73120000
Notice published8 August 2024

What it is for

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

Read the original award notice on Contracts Finder →

Other contracts from this buyer

270 awards on file, worth £337.3m.

Everything DSIT has awarded →

Other contracts won by this supplier

1 award on file, worth £440k.

Everything Grey Swan Security Inc has won →