6 citations · 26 across the 15 of their papers we have counts for
17 papers
VNN-LIB 2.0: Rigorous Foundations for Neural Network Verification
Ann Roy, Allen Antony, Andrea Gimelli +1
Neural network verification is an active and rapidly maturing research area, with a growing ecosystem of solvers and tools. The VNN-LIB standard was introduced to support interoper…
Adequate Losses via Quantitative Linear Logic
Matteo Capucci, Robert Atkey, Charles Grellois +2
As neural components are increasingly embedded in existing symbolic software -- including safety-critical systems -- the question arises of how to specify and enforce the safety of…
Neural Network Verification is a Programming Language Challenge
Lucas C. Cordeiro, Matthew L. Daggitt, Julien Girard-Satabin +8
Neural network verification is a new and rapidly developing field of research. So far, the main priority has been establishing efficient verification algorithms and tools, while pr…
NLP Verification: Towards a General Methodology for Certifying Robustness
Marco Casadio, Tanvi Dinkar, Ekaterina Komendantskaya +6
Machine Learning (ML) has exhibited substantial success in the field of Natural Language Processing (NLP). For example large language models have empirically proven to be capable o…
Compiling High-Level Neural Network Specifications into VNN-LIB Queries
Matthew L. Daggitt, Wen Kokke, Robert Atkey
The formal verification of traditional software has been revolutionised by verification-orientated languages such as Dafny and F* which enable developers to write high-level specif…
Marabou 2.0: A Versatile Formal Analyzer of Neural Networks
Haoze Wu, Omri Isac, Aleksandar Zeljić +14
This paper serves as a comprehensive system description of version 2.0 of the Marabou framework for formal analysis of neural networks. We discuss the tool's architectural design a…
Vehicle: Bridging the Embedding Gap in the Verification of Neuro-Symbolic Programs
Matthew L. Daggitt, Wen Kokke, Robert Atkey +3
Neuro-symbolic programs, i.e. programs containing both machine learning components and traditional symbolic code, are becoming increasingly widespread. Finding a general methodolog…
ANTONIO: Towards a Systematic Method of Generating NLP Benchmarks for Verification
Marco Casadio, Luca Arnaboldi, Matthew L. Daggitt +5
Verification of machine learning models used in Natural Language Processing (NLP) is known to be a hard problem. In particular, many known neural network verification methods that…
Logic of Differentiable Logics: Towards a Uniform Semantics of DL
Natalia Ślusarz, Ekaterina Komendantskaya, Matthew L. Daggitt +2
Differentiable logics (DL) have recently been proposed as a method of training neural networks to satisfy logical specifications. A DL consists of a syntax in which specifications…
Differentiable Logics for Neural Network Training and Verification
Natalia Slusarz, Ekaterina Komendantskaya, Matthew L. Daggitt +1
The rising popularity of neural networks (NNs) in recent years and their increasing prevalence in real-world applications have drawn attention to the importance of their verificati…
Why Robust Natural Language Understanding is a Challenge
Marco Casadio, Ekaterina Komendantskaya, Verena Rieser +4
With the proliferation of Deep Machine Learning into real-life applications, a particular property of this technology has been brought to attention: robustness Neural Networks noto…
Vehicle: Interfacing Neural Network Verifiers with Interactive Theorem Provers
Matthew L. Daggitt, Wen Kokke, Robert Atkey +2
Verification of neural networks is currently a hot topic in automated theorem proving. Progress has been rapid and there are now a wide range of tools available that can verify pro…
Formally Verified Convergence of Policy-Rich DBF Routing Protocols
Matthew L. Daggitt, Timothy G. Griffin
In this paper we present new general convergence results about the behaviour of the Distributed Bellman-Ford (DBF) family of routing protocols, which includes distance-vector proto…
Actions You Can Handle: Dependent Types for AI Plans
Alasdair Hill, Ekaterina Komendantskaya, Matthew L. Daggitt +1
Verification of AI is a challenge that has engineering, algorithmic and programming language components. For example, AI planners are deployed to model actions of autonomous agents…
Neural Network Robustness as a Verification Property: A Principled Case Study
Marco Casadio, Ekaterina Komendantskaya, Matthew L. Daggitt +4
Neural networks are very successful at detecting patterns in noisy data, and have become the technology of choice in many fields. However, their usefulness is hampered by their sus…
Dynamic Asynchronous Iterations
Matthew L. Daggitt, Timothy G. Griffin
Many problems can be solved by iteration by multiple participants (processors, servers, routers etc.). Previous mathematical models for such asynchronous iterations assume a single…
Tracking Urban Activity Growth Globally with Big Location Data
Matthew Daggitt, Anastasios Noulas, Blake Shaw +1
In recent decades the world has experienced rates of urban growth unparalleled in any other period of history and this growth is shaping the environment in which an increasing prop…