SyReNN: A Tool for Analyzing Deep Neural Networks
This tool aims to help researchers and practitioners understand and analyze deep neural networks, particularly for low-dimensional input space analyses, addressing issues like vulnerabilities and buggy behavior.
This paper introduces SyReNN, a tool for analyzing deep neural networks by computing their symbolic representation through decomposition into linear functions. The tool is evaluated on three case studies: computing Integrated Gradients, visualizing decision boundaries, and patching a DNN.
Deep Neural Networks (DNNs) are rapidly gaining popularity in a variety of important domains. Formally, DNNs are complicated vector-valued functions which come in a variety of sizes and applications. 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 its symbolic representation. The key insight is to decompose the DNN into linear functions. Our tool is designed for analyses using low-dimensional subsets of 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 patching a DNN.