Algorithms for verifying deep neural networks

C Liu, T Arnon, C Lazarus, C Strong… - … and Trends® in …, 2021 - nowpublishers.com
Deep neural networks are widely used for nonlinear function approximation, with
applications ranging from computer vision to control. Although these networks involve the …

Assuring the machine learning lifecycle: Desiderata, methods, and challenges

R Ashmore, R Calinescu, C Paterson - ACM Computing Surveys (CSUR), 2021 - dl.acm.org
Machine learning has evolved into an enabling technology for a wide range of highly
successful applications. The potential for this success to continue and accelerate has placed …

A survey of zero-shot generalisation in deep reinforcement learning

R Kirk, A Zhang, E Grefenstette, T Rocktäschel - Journal of Artificial …, 2023 - jair.org
The study of zero-shot generalisation (ZSG) in deep Reinforcement Learning (RL) aims to
produce RL algorithms whose policies generalise well to novel unseen situations at …

General cutting planes for bound-propagation-based neural network verification

H Zhang, S Wang, K Xu, L Li, B Li… - Advances in neural …, 2022 - proceedings.neurips.cc
Bound propagation methods, when combined with branch and bound, are among the most
effective methods to formally verify properties of deep neural networks such as correctness …

Delivering trustworthy AI through formal XAI

J Marques-Silva, A Ignatiev - Proceedings of the AAAI Conference on …, 2022 - ojs.aaai.org
The deployment of systems of artificial intelligence (AI) in high-risk settings warrants the
need for trustworthy AI. This crucial requirement is highlighted by recent EU guidelines and …

Are formal methods applicable to machine learning and artificial intelligence?

M Krichen, A Mihoub, MY Alzahrani… - … Conference of Smart …, 2022 - ieeexplore.ieee.org
Formal approaches can provide strict correctness guarantees for the development of both
hardware and software systems. In this work, we examine state-of-the-art formal methods for …

NNV: the neural network verification tool for deep neural networks and learning-enabled cyber-physical systems

HD Tran, X Yang, D Manzanas Lopez, P Musau… - … on Computer Aided …, 2020 - Springer
This paper presents the Neural Network Verification (NNV) software tool, a set-based
verification framework for deep neural networks (DNNs) and learning-enabled cyber …

Sok: Certified robustness for deep neural networks

L Li, T **e, B Li - 2023 IEEE symposium on security and privacy …, 2023 - ieeexplore.ieee.org
Great advances in deep neural networks (DNNs) have led to state-of-the-art performance on
a wide range of tasks. However, recent studies have shown that DNNs are vulnerable to …

First three years of the international verification of neural networks competition (VNN-COMP)

C Brix, MN Müller, S Bak, TT Johnson, C Liu - International Journal on …, 2023 - Springer
This paper presents a summary and meta-analysis of the first three iterations of the annual
International Verification of Neural Networks Competition (VNN-COMP), held in 2020, 2021 …

The second international verification of neural networks competition (vnn-comp 2021): Summary and results

S Bak, C Liu, T Johnson - arxiv preprint arxiv:2109.00498, 2021 - arxiv.org
This report summarizes the second International Verification of Neural Networks
Competition (VNN-COMP 2021), held as a part of the 4th Workshop on Formal Methods for …