gvtcx

Explainability for Vulnerability Identification in AI Systems

Defence Science and Technology Laboratory Published 24 Aug 2022 Contracts Finder

key details

Value£149,717
Statuscomplete
Category (CPV) 48000000
Deadline8 Jul 2022
Contract start1 Sept 2022
Contract end31 Aug 2023
Proceduredirect
SME suitableYes
OCIDocds-b5fd17-00a2575c-79f5-4d35-9d5f-abc8fa2c317c

Award

SupplierValueDateStatus
City, University of London £149,717 3 Aug 2022 active

description

The Research and Development submission to the Strategic Review (SR20) recognised the need to advance MOD's ability to adopt critical and game-changing technology, enabling autonomous systems on the battlefield and in the command space through the use of artificial intelligence. It proposed to do this by establishing a Defence AI Centre with the science and technology component delivered by a Defence AI Centre Experimentation hub (DAIC-X) led by Dstl.

A key objective for DAIC-X is to understand and develop good practice in managing AI verification, validation, vulnerabilities as well as wider issues including trust and transparency and legal and ethical considerations.

This task will research the potential to exploit artificial intelligence explainability (XAI) methodologies to identify and expose vulnerabilities in neural network-based machine vision algorithms.

Please see the attached Tasking Form for further information regarding this award.

notice history

1 notice published against this procurement.

PublishedTypeRegimeNotice
24 Aug 2022 Award (award) · 32b71324-c3b8-4715-a708-db4659db552a-566358

more from Defence Science and Technology Laboratory

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.

source

Published on Contracts Finder. Contact details for named individuals are not reproduced on this site.