Saved in:
Bibliographic Details
Main Authors: Fukuda, Kota, Zhang, Guanqin, Zhang, Zhenya, Sui, Yulei, Zhao, Jianjun
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2505.00963
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912357605703680
author Fukuda, Kota
Zhang, Guanqin
Zhang, Zhenya
Sui, Yulei
Zhao, Jianjun
author_facet Fukuda, Kota
Zhang, Guanqin
Zhang, Zhenya
Sui, Yulei
Zhao, Jianjun
contents Formal verification is a rigorous approach that can provably ensure the quality of neural networks, and to date, Branch and Bound (BaB) is the state-of-the-art that performs verification by splitting the problem as needed and applying off-the-shelf verifiers to sub-problems for improved performance. However, existing BaB may not be efficient, due to its naive way of exploring the space of sub-problems that ignores the \emph{importance} of different sub-problems. To bridge this gap, we first introduce a notion of ``importance'' that reflects how likely a counterexample can be found with a sub-problem, and then we devise a novel verification approach, called ABONN, that explores the sub-problem space of BaB adaptively, in a Monte-Carlo tree search (MCTS) style. The exploration is guided by the ``importance'' of different sub-problems, so it favors the sub-problems that are more likely to find counterexamples. As soon as it finds a counterexample, it can immediately terminate; even though it cannot find, after visiting all the sub-problems, it can still manage to verify the problem. We evaluate ABONN with 552 verification problems from commonly-used datasets and neural network models, and compare it with the state-of-the-art verifiers as baseline approaches. Experimental evaluation shows that ABONN demonstrates speedups of up to $15.2\times$ on MNIST and $24.7\times$ on CIFAR-10. We further study the influences of hyperparameters to the performance of ABONN, and the effectiveness of our adaptive tree exploration.
format Preprint
id arxiv_https___arxiv_org_abs_2505_00963
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Adaptive Branch-and-Bound Tree Exploration for Neural Network Verification
Fukuda, Kota
Zhang, Guanqin
Zhang, Zhenya
Sui, Yulei
Zhao, Jianjun
Machine Learning
Programming Languages
Formal verification is a rigorous approach that can provably ensure the quality of neural networks, and to date, Branch and Bound (BaB) is the state-of-the-art that performs verification by splitting the problem as needed and applying off-the-shelf verifiers to sub-problems for improved performance. However, existing BaB may not be efficient, due to its naive way of exploring the space of sub-problems that ignores the \emph{importance} of different sub-problems. To bridge this gap, we first introduce a notion of ``importance'' that reflects how likely a counterexample can be found with a sub-problem, and then we devise a novel verification approach, called ABONN, that explores the sub-problem space of BaB adaptively, in a Monte-Carlo tree search (MCTS) style. The exploration is guided by the ``importance'' of different sub-problems, so it favors the sub-problems that are more likely to find counterexamples. As soon as it finds a counterexample, it can immediately terminate; even though it cannot find, after visiting all the sub-problems, it can still manage to verify the problem. We evaluate ABONN with 552 verification problems from commonly-used datasets and neural network models, and compare it with the state-of-the-art verifiers as baseline approaches. Experimental evaluation shows that ABONN demonstrates speedups of up to $15.2\times$ on MNIST and $24.7\times$ on CIFAR-10. We further study the influences of hyperparameters to the performance of ABONN, and the effectiveness of our adaptive tree exploration.
title Adaptive Branch-and-Bound Tree Exploration for Neural Network Verification
topic Machine Learning
Programming Languages
url https://arxiv.org/abs/2505.00963