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 …

NNV 2.0: the neural network verification tool

DM Lopez, SW Choi, HD Tran, TT Johnson - International Conference on …, 2023 - Springer
This manuscript presents the updated version of the Neural Network Verification (NNV) tool.
NNV is a formal verification software tool for deep learning models and cyber-physical …

Polar: A polynomial arithmetic framework for verifying neural-network controlled systems

C Huang, J Fan, X Chen, W Li, Q Zhu - International Symposium on …, 2022 - Springer
We present POLAR (The source code can be found at https://github. com/ChaoHuang2018/
POLAR_Tool. The full version of this paper can be found at https://arxiv …

ARCH-COMP23 category report: Artificial intelligence and neural network control systems (AINNCS) for continuous and hybrid systems plants

DM Lopez, M Althoff, M Forets… - EPiC Series in …, 2023 - mediatum.ub.tum.de
This report presents the results of a friendly competition for formal verification of continuous
and hybrid systems with artificial intelligence (AI) components. Specifically, machine …

Safety verification of decision-tree policies in continuous time

C Schilling, A Lukina, E Demirović… - Advances in Neural …, 2023 - proceedings.neurips.cc
Decision trees have gained popularity as interpretable surrogate models for learning-based
control policies. However, providing safety guarantees for systems controlled by decision …

Efficient interaction-aware interval analysis of neural network feedback loops

S Jafarpour, A Harapanahalli… - IEEE Transactions on …, 2024 - ieeexplore.ieee.org
In this article, we propose a computationally efficient framework for interval reachability of
systems with neural network controllers. Our approach leverages inclusion functions for the …

Polar-express: Efficient and precise formal reachability analysis of neural-network controlled systems

Y Wang, W Zhou, J Fan, Z Wang, J Li… - … on Computer-Aided …, 2023 - ieeexplore.ieee.org
Neural networks (NNs) playing the role of controllers have demonstrated impressive
empirical performance on challenging control problems. However, the potential adoption of …

Provably Safe Neural Network Controllers via Differential Dynamic Logic

S Teuber, S Mitsch, A Platzer - arxiv preprint arxiv:2402.10998, 2024 - arxiv.org
While neural networks (NNs) have a large potential as goal-oriented controllers for Cyber-
Physical Systems, verifying the safety of neural network based control systems (NNCSs) …

Tutorial: Neural Network and Autonomous Cyber-Physical Systems Formal Verification for Trustworthy AI and Safe Autonomy

HD Tran, D Manzanas Lopez, T Johnson - Proceedings of the …, 2023 - dl.acm.org
This interactive tutorial describes state-of-the-art methods for formally verifying neural
networks and their usage within safety-critical cyber-physical systems (CPS). The inclusion …

Neural abstraction-based controller synthesis and deployment

R Majumdar, M Salamati, S Soudjani - ACM Transactions on Embedded …, 2023 - dl.acm.org
Abstraction-based techniques are an attractive approach for synthesizing correct-by-
construction controllers to satisfy high-level temporal requirements. A main bottleneck for …