NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
NNV: The Neural Network Verification Tool for Deep Neural Networks and Learning-Enabled Cyber-Physical Systems
复制标题
DOI：
10.1007/978-3-030-53288-8_1
复制
发表时间：
2020-06-13
期刊：
影响因子：
--
通讯作者：
Johnson TT
中科院分区：
文献类型：
--
作者：
Tran HD;Yang X;Manzanas Lopez D;Musau P;Nguyen LV;Xiang W;Bak S;Johnson TT
本文介绍了神经网络验证（NNV）软件工具，这是一个基于集合的验证框架，用于深度神经网络（DNN）和支持学习的网络物理系统（CPS）。NNV的核心是一组可达性算法，这些算法利用了各种集合表示，如多面体、星星集、zonotopes和抽象域表示。NNV支持精确（健全和完整）和过近似（健全）可达性算法，用于验证具有各种激活函数的前馈神经网络（FFNN）的安全性和鲁棒性。对于支持学习的CPS，例如包含神经网络的闭环控制系统，NNV为线性对象模型和具有分段线性激活函数（例如ReLU）的FFNN控制器提供精确和过近似的可达性分析方案。对于类似的神经网络控制系统（NNCS），而不是具有非线性的植物模型，NNV支持过近似的分析相结合的星星集分析用于FFNN控制器与zonotope-based分析的非线性植物动态CORA的建设。我们使用两个真实案例研究来评估NNV：第一个是ACAS Xu网络的安全性验证，第二个是基于深度学习的自适应巡航控制系统的安全性验证。
This paper presents the Neural Network Verification (NNV) software tool, a set-based verification framework for deep neural networks (DNNs) and learning-enabled cyber-physical systems (CPS). The crux of NNV is a collection of reachability algorithms that make use of a variety of set representations, such as polyhedra, star sets, zonotopes, and abstract-domain representations. NNV supports both exact (sound and complete) and over-approximate (sound) reachability algorithms for verifying safety and robustness properties of feed-forward neural networks (FFNNs) with various activation functions. For learning-enabled CPS, such as closed-loop control systems incorporating neural networks, NNV provides exact and over-approximate reachability analysis schemes for linear plant models and FFNN controllers with piecewise-linear activation functions, such as ReLUs. For similar neural network control systems (NNCS) that instead have nonlinear plant models, NNV supports over-approximate analysis by combining the star set analysis used for FFNN controllers with zonotope-based analysis for nonlinear plant dynamics building on CORA. We evaluate NNV using two real-world case studies: the first is safety verification of ACAS Xu networks, and the second deals with the safety verification of a deep learning-based adaptive cruise control system.
登录
查看更多内容
DOI：
10.1007/978-3-030-53288-8_2
发表时间：
2020-06-13
期刊：
Computer Aided Verification
影响因子：
--
作者：
Tran HD;Bak S;Xiang W;Johnson TT
通讯作者：
Johnson TT
影响因子：
2
作者：
Huang, Chao;Fan, Jiameng;Zhu, Qi
通讯作者：
Zhu, Qi
影响因子：
2
作者：
Hoang-Dung Tran;Cai, Feiyang;Koutsoukos, Xenofon
通讯作者：
Koutsoukos, Xenofon
影响因子：
22.7
作者：
Krizhevsky, Alex;Sutskever, Ilya;Hinton, Geoffrey E.
通讯作者：
Hinton, Geoffrey E.
影响因子：
5
作者：
Goldberg, Yoav
通讯作者：
Goldberg, Yoav