A review of abstraction methods towards verifying neural networks
Open Access
- 10 June 2024
- journal article
- review article
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Embedded Computing Systems
- Vol. 23 (4) , 1-19
Abstract
Neural networks as a machine learning technique are increasingly deployed in various domains. Despite their performance and their continuous improvement, the deployment of neural networks in safety-critical systems, in particular for autonomous mobility, remains restricted. This is mainly due to the lack of (formal) specifications and verification methods and tools that allow for having sufficient confidence in the behavior of the neural-network-based functions. Recent years have seen neural network verification getting more attention; many verification methods were proposed, yet the practical applicability of these methods to real-world neural network models remains limited. The main challenge of neural network verification methods is related to the computational complexity and the large size of neural networks pertaining to complex functions. As a consequence, applying abstraction methods for neural network verification purposes is seen as a promising mean to cope with such issues. The aim of abstraction is to build an model by omitting some irrelevant details or some details that are not highly impacting w.r.t some considered features. Thus, the verification process is made faster and easier while preserving, to some extent, the relevant behavior regarding the properties to be examined on the original model. In this article, we review both the abstraction techniques for activation functions and model size reduction approaches, with a particular focus on the latter. The review primarily discusses the application of abstraction techniques on feed-forward neural networks and explores the potential for applying abstraction to other types of neural networks. Throughout the article, we present the main idea of each approach and then discuss its respective advantages and limitations in detail. Finally, we provide some insights and guidelines to improve the discussed methods.Keywords
Funding Information
- French Program “Investissements d’Avenir”
- French collaborative project TASV
This publication has 36 references indexed in Scilit:
- The Marabou Framework for Verification and Analysis of Deep Neural Networks2019
- An abstract domain for certifying neural networksProceedings of the ACM on Programming Languages, 2019
- The Autonomous Train2018
- AI2: Safety and Robustness Certification of Neural Networks with Abstract Interpretation2018
- DroNet: Learning to Fly by DrivingIEEE Robotics and Automation Letters, 2018
- Formal Verification of Piece-Wise Linear Feed-Forward Neural Networks2017
- Reluplex: An Efficient SMT Solver for Verifying Deep Neural Networks2017
- Safety Verification of Deep Neural Networks2017
- A survey of deep neural network architectures and their applicationsNeurocomputing, 2017
- An Abstraction-Refinement Approach to Verification of Artificial Neural Networks2010