AISEC outputs

Publications

Neural Networks, Secure by Construction: An Exploration of Refinement Types

Wen Kokke, Ekaterina Komendantskaya, Daniel Kienitz, Bob Atkey, David Aspinall. 
The 18th Asian Symposium on Programming Languages and Systems
2020. Read here
Topics: Programming Languages, Verification

Relative Robustness of Quantized Neural Networks Against Adversarial Attacks

Kirsty Duncan, Ekaterina Komendantskaya, Robert Stewart, Michael Lones
2020 International Joint Conference on Neural Networks
2020. Read here
Topics: Verification

Continuous Verification of Machine Learning: a Declarative Programming Approach

Ekaterina Komendantskaya, Wen Kokke, Daniel Kienitz
22nd International Symposium on Principles and Practice of Declarative Programming
2020. Read here
Topics: Verification, Programming Languages

Property-driven Training: All You (N)Ever Wanted to Know About

Marco Casadio, Matthew Daggitt, Ekaterina Komendantskaya, Wen Kokke, Daniel Kienitz, Rob Stewart
Under submission
2021. Read here
Topics: Verification

Actions You Can Handle: Dependent Types for AI Plans

Alasdair Hill, Ekaterina Komendantskaya, Matthew Daggitt, Ronald P. A. Petrick
Workshop on Type-driven Development'21, at ICFP'21
2021. Read here
Topics: Verification

A type- and scope-safe universe of syntaxes with binding: their semantics and proofs

Guillaume Allais, Robert Atkey, James Chapman, Conor McBride, and James McKinna
Journal of Functional Programming
2021. Read here
Topics: Programming Languages

Optimising Hardware Accelerated Neural Networks with Quantisation and a Knowledge Distillation Evolutionary Algorithm

Robert Stewart, Andrew Nowlan, Pascal Bacchus, Quentin Ducasse, Ekaterina Komendantskaya
Under submission
2021. Read here
Topics: Other

A Framework for Substructural Type Systems

James Wood and Robert Atkey
31st European Symposium on Programming
2022. To appear
Topics: Verification

Vehicle: Interfacing Neural Network Verifiers with Interactive Theorem Provers

Matthew Daggitt, Wen Kokke, Robert Atkey, Luca Arnaboldi, and Ekaterina Komendantskaya
Under submission
2022. Read here
Topics: Programming Languages, Verification

Neural Network Verification in Imandra: a Holistic Approach

Remi Desmartin, Ekaterina Komendantskaya, Matthew Daggitt and Grant Passmore
Under submission
2022. To appear
Topics: Verification

Proof-Carrying Plans: a Resource Logic for AI Planning

Alistair Hill, Ekaterina Komendantskaya, Ron Petrick 
22nd International Symposium on Principles and Practice of Declarative Programming
2020. Read here
Topics: Verification

Accuracy, Training Time and Hardware Efficiency Trade-Offs for Quantized Neural Networks on FPGAs

Pascal Bacchus, Rob Stewart, Ekaterina Komendantskya
Architectures, Tools, and Applications - 16th International Symposium
2020. Read here
Topics: Other

Neural Networks, Secure by Construction

Wen Kokke, Ekaterina Komendantskya, Daniel Kienitz, Robert Atkey, David Aspinall
Programming Languages and Systems - 18th Asian Symposium
2020. Read here
Topics: Verification, Programming Languages

The Effect of Manifold Entanglement and Intrinsic Dimensionality on Learning

Daniel Keinitz, Ekaterina Komendantskya, Michael Lones
36th AAAI Conference on Artificial Intelligence
2020. To appear
Topics: Other

Automating Cryptographic Protocol Language Generation from Structured Specifications

Roberto Metere & Luca Arnaboldi
Under submission
2022. To appear
Topics: Security

Explainable Machine Learning-driven Strategy for Automated Trading Pattern Extraction

Artur Sokolovsky, Luca Arnaboldi, Jaume Bacardit, Thomas Groß.
Under submission
2022. Read here
Topics: Other

Machine learning classification of price extrema based on market microstructure features: A case study of s&p500 e-mini futures

Artur Sokolovsky, Luca Arnaboldi
Under submission
2022. Read here
Topics: Other

Garbage In, Toxic Data Out: A proposal for Ethical Artificial Intelligence Sustainability Impact Statements

Ronny Bogani, A. Theodorou, Luca Arnaboldi, R. H Wortham
Under submission
2022. To appear
Topics: Security, Law

Smart automotive technology adherence to the law: (de)constructing road rules for autonomous system development, verification and safety

Scott ​​McLachlan, Martin Neil, Kudakwashe Dube, Ronny Bogani, Norman Fenton, Burkhard Schafer
International Journal of Law and Information Technology
2022. Read here
Topics: Law

The Self-Driving Car: Crossroads at the bleeding edge of Artificial Intelligence and Law

Scott McLachlan, Evangelia Kyrimi, Kudakwashe Dube, Norman Fenton, Burkhard Schafer
Under submission
2022. Read here
Topics: Law

How might Driver Licensing and Vehicle Registration evolve if we adopt Autonomous Cars and Digital Identification?

Scott McLachlan, Ronny Bogani, Burkhard Schafer
Under submission
2022. Read here
Topics: Law

Too many moving parts: Autonomous vehicles and the modelling of complex technico-legal systems

Scott McLachlan, Burkhard Schafer
BILETA Conference
2021. To appear
Topics: Law

AnalyZr: A Python application for zircon grain image segmentation and shape analysis

Taryn Scharf, Chris Kirkland, Matthew Daggitt, Milo Barham, Vladimir Puzyrev
Computers & Geosciences
2022 Read here
Topics: Other

Dynamic Asynchronous Iterations

Matthew Daggitt, Timothy Griffin
Under submission
2022 Read here
Topics: Other

Talks

Safety for E2E Conversational AI: Opportunities and Challenges

Verena Rieser
The European Chatbot & Conversational AI Summit
February 4th & 5th, 2021

Neural network verification as program synthesis

Ekaterina Komendantskaya, Matthew Daggitt
The Katz Lab, the Hebrew University of Jerusalem
18th of March, 2021

Analyse, search, reason, interpret, verify: the “Maslow Pyramid” of AI modelling

Ekaterina Komendantskaya, Alasdair HIll
Invited talk at TAS Governance Node
23rd of June, 2021

A DSL for embedding constraints in neural networks: from training to termination

Matthew Daggitt
Scottish Programming Language Seminars
20th of October, 2021

Integrating Agda with SMT-LIB – An incomplete list of pits I fell in

Wen Kokke
Keynote talk at  Workshop on Type-Driven Development 2021
22nd of August, 2021

Datatypes with Negation

Robert Atkey
Workshop on Mathematically Structured Functional Programming 2022
2nd of April, 2022

Neural network robustness… careful what you verify!

Matthew Daggitt
Workshop on Formal Methods in AI 2021
15th of April, 2022

Using Dependent Types at Scale: Maintaining the Agda Standard Library

Matthew Daggitt
Workshop on Implementation of Type Systems 202
22nd of January, 2022

Analyse, search, reason, interpret, verify: the “Maslow Pyramid” of AI modelling

Ekaterina Komendantskya
Trustworthy Autonomous System Consortium
23rd of June, 2021

Interfacing NN verifiers with ITPs

Matthew Daggitt
Initial Types Club. Chalmers University of Technology
10th of February, 2022

Organisation

Workshop - Safety for Conversational AI

Verena Rieser (program chair)
Safety for Conversational AI
October 17th, 2020

Special session - Safety for E2E Conversational AI

Verena Rieser (organising committee)
Special Interest Group on Discourse and Dialogue 2021
July 29th - 31st, 2021

Outreach

How to make a chatbot that isn’t racist or sexist

Verena Rieser et al.
MIT Technology Review
23rd of October, 2020

Perfecting self-driving cars – can it be done?

Ekaterina Komendantskaya, Matthew Daggitt, Luca Arnaboldi
The Conversation
7th of April, 2021

Is the Dream of Self-Driving Cars Dead?  (quoted)

Ekaterina Komendantskaya, Matthew Daggitt, Luca Arnaboldi
DirectIndustry magazine
26th of October, 2021

Free Joomla! templates by Engine Templates