BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks
Abstract
Verifying and explaining the behavior of neural networks is becoming increasingly important, especially when they are deployed in safety-critical applications. In this paper, we study verification problems for Binarized Neural Networks (BNNs), the 1-bit quantization of general real-numbered neural networks. Our approach is to encode BNNs into Binary Decision Diagrams (BDDs), which is done by exploiting the internal structure of the BNNs. In particular, we translate the input-output relation of blocks in BNNs to cardinality constraints which are then encoded by BDDs. Based on the encoding, we develop a quantitative verification framework for BNNs where precise and comprehensive analysis of BNNs can be performed. We demonstrate the application of our framework by providing quantitative robustness analysis and interpretability for BNNs. We implement a prototype tool BDD4BNN and carry out extensive experiments which confirm the effectiveness and efficiency of our approach.
Cite
@article{arxiv.2103.07224,
title = {BDD4BNN: A BDD-based Quantitative Analysis Framework for Binarized Neural Networks},
author = {Yedi Zhang and Zhe Zhao and Guangke Chen and Fu Song and Taolue Chen},
journal= {arXiv preprint arXiv:2103.07224},
year = {2021}
}