New Project and Vacancies

We are starting a big, multi-site and multi-million project on AI verification in September 2020! The project AISEC: AI Secure and Explainable by Construction is funded by EPSRC, and will investigate novel methods of AI verification in Autonomous vehicles and conversational agents. We are looking for Research assistants and PhD students: see http://laiv.uk/index.php/vacancies/

LAIV paper at IJCNN’20

Many congratulations to all for having the following paper accepted:

Kirsty Duncan, Ekaterina Komendantskaya, Robert Sewart, Michael Lones: 

Relative Robustness of Quantized Neural Networks Against Adversarial Attacks

accepted to be published and presented at the International Joint Conference on Neural Networks, IJCNN’20, part of the World Congress on Computational Intelligence: https://wcci2020.org/ 19-24 July 2020, Glasgow, Scotland.

LAIV during COVID-19 outbreak

Dear fellow researchers and friends, it is good to remember that LAIV continues, and in particular LAIV seminars continue, albeit on-line. This Wednesday we will be testing Zoom meetings, with the view to have our first proper seminar next Wednesday. Information how to join LAIV seminars on-line will be updated on LAIV Seminars page. In the meantime, keep safe and keep busy!

LAIV’s second Research Grant

LAIV team won its second research grant: CONVENER: Continuous Verification of Neural Networks, funded by the UK Research Institute in Verified Trustworthy Software Systems (VETSS) , as part of “Digital Security Through Verification” call. Grant holders: E.Komendantskaya and D.Aspinall, named RAs: Wen Kokke and Daniel Kienitz.

Research paper

Many congratulations to the team for having the paper Accuracy, Training Time and Hardware Efficiency Trade-Offs for Quantised Neural Networks on FPGAs, by Pascal Bacchus, Robert Stewart and Ekaterina Komendantskaya accepted at 16th International Symposium on Applied Reconfigurable Computing (ARC2020), 1-3 April   Toledo, Spain.

New LAIV members

We welcome several new members to LAIV team: the new cohort of MSc students: Alexandre, Marco Vincent, to work on topics in Neural Net verification, and Wen Kokke (from Edinburgh University) as an RA in the Neural Networks with Security Contracts grant.

LAIV’s first research grant

We are very proud to announce the first successful research funding bid by LAIV team: NCSC-funded research project SecCon-NN: Neural Networks with Security Contracts — towards lightweight, modular security for neural networks. Funded as part of NCSC “Security for AI” call.

LAIV’s first MSc Cohort finishes MSc studies

LAIV MSc students Pierre, Pascal and Daniel have just finished their MSc, with Master Theses on Neural Net verification, scoring 85%, 85% and 95% respectively, and the Best Dissertation Award for the latter. Congratulations and very well done! Good luck with your further studies, research and careers! And welcome to your PhD in LAIV group, Daniel!