SyReNN: A Tool for Analyzing Deep Neural Networks
SyReNN: A Tool for Analyzing Deep Neural Networks
复制标题
DOI：
10.1007/s10009-023-00695-1
复制
发表时间：
2021-01
期刊：
影响因子：
--
通讯作者：
Matthew Sotoudeh;Zhen-Zhong Tao;Aditya V. Thakur
中科院分区：
文献类型：
--
作者：
Matthew Sotoudeh;Zhen-Zhong Tao;Aditya V. Thakur
深度神经网络（DNN）在各种重要领域迅速普及。不幸的是，现代DNN已经被证明容易受到各种攻击和错误行为的影响。这促使最近的工作正式分析这种DNN的属性。本文介绍了SyReNN，这是一个通过计算DNN的符号表示来理解和分析DNN的工具，其关键在于将DNN分解为线性函数。我们的工具是专为使用输入空间的低维子集进行分析而设计的，这是DNN分析工具空间中的独特设计点。我们描述的工具和基本理论，然后评估其使用和性能的三个案例研究：计算集成的代理，可视化的DNN的决策边界，并修复错误的DNN。
Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Unfortunately, modern DNNs have been shown to be vulnerable to a variety of attacks and buggy behavior. This has motivated recent work in formally analyzing the properties of such DNNs. This paper introduces SyReNN, a tool for understanding and analyzing a DNN by computing itssymbolic representation.The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses usinglow-dimensional subsetsof the input space, a unique design point in the space of DNN analysis tools. We describe the tool and the underlying theory, then evaluate its use and performance on three case studies: computing Integrated Gradients, visualizing a DNN’s decision boundaries, and repairing buggy DNNs.