ShanghaiTech University Knowledge Management System
BDD4BNN: A BDD-Based Quantitative Analysis Framework for Binarized Neural Networks | |
2021 | |
会议录名称 | PROCEEDINGS OF THE 33RD INTERNATIONAL CONFERENCE ON COMPUTER AIDED VERIFICATION, CAV 2021 (IF:0.402[JCR-2005],0.000[5-Year]) |
ISSN | 0302-9743 |
卷号 | 12759 |
页码 | 175-200 |
发表状态 | 已发表 |
DOI | 10.1007/978-3-030-81685-8_8 |
摘要 | 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 and interpretability 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 in turn encoded by BDDs. Based on the encoding, we develop a quantitative 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, confirming the effectiveness and efficiency of our approach. |
收录类别 | EI ; CPCI ; CPCI-S |
语种 | 英语 |
WOS研究方向 | Computer Science |
WOS类目 | Computer Science, Hardware & Architecture ; Computer Science, Software Engineering ; Computer Science, Theory & Methods |
WOS记录号 | WOS:000698732400008 |
出版者 | SPRINGER INTERNATIONAL PUBLISHING AG |
原始文献类型 | Proceedings Paper |
引用统计 | 正在获取...
|
文献类型 | 会议论文 |
条目标识符 | https://kms.shanghaitech.edu.cn/handle/2MSLDSTB/128429 |
专题 | 信息科学与技术学院_博士生 信息科学与技术学院_PI研究组_宋富组 |
通讯作者 | Song, Fu |
作者单位 | 1.ShanghaiTech Univ, Shanghai, Peoples R China; 2.Shanghai Engn Res Ctr Intelligent Vis & Imaging, Shanghai, Peoples R China; 3.Birkbeck Univ London, London, England |
第一作者单位 | 上海科技大学 |
通讯作者单位 | 上海科技大学 |
第一作者的第一单位 | 上海科技大学 |
推荐引用方式 GB/T 7714 | Zhang, Yedi,Zhao, Zhe,Chen, Guangke,et al. BDD4BNN: A BDD-Based Quantitative Analysis Framework for Binarized Neural Networks[C]:SPRINGER INTERNATIONAL PUBLISHING AG,2021:175-200. |
条目包含的文件 | ||||||
文件名称/大小 | 文献类型 | 版本类型 | 开放类型 | 使用许可 |
修改评论
除非特别说明,本系统中所有内容都受版权保护,并保留所有权利。