[TYPES/announce] Postdoc in Foundational Security for AI at University of Edinburgh, UK

David Aspinall David.Aspinall at ed.ac.uk
Fri Jul 31 11:19:53 EDT 2020


Postdoc in Foundational Security for AI at University of Edinburgh, UK
======================================================================

Applications are invited for a Research Assistant in Security for AI,
working in the School of Informatics, University of Edinburgh. This
post is part of the project

  AISEC - AI Secure and Explainable by Construction

a UKRI research project on Security for Artificial Intelligence
running 2020-23, joint with Heriot-Watt University and University of 
Strathclyde.

The AISEC project aims to design and implement a methodology and
development environment for "policy-to-property" verification of
complex AI systems which are secure and explainable by
construction. The project will employ types systems and supporting
lightweight verification methods to help document, implement and
refine policies for complex deep learning and rules-based
systems.  Types will serve as a unifying mechanism to embed security
and safety contracts directly into programs that implement AI.

The project will examine two key AI application areas: autonomous
vehicles and natural language interfaces and it includes collaboration
with legal researchers and industrial partners in each application
area.

An ideal background for this post would encompass some foundational
aspects of security (programming language based or other approaches),
with some knowledge of current AI methods.

For more details, please see:

* https://laiv.uk/vacancies/ - about the project
* https://edin.ac/339zEUB    - about the job and to apply

Application deadline: 7th September.

For informal enquiries, please contact David Aspinall
(David.Aspinall at ed.ac.uk).


-- 
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.



More information about the Types-announce mailing list