SyReNN: A Tool for Analyzing Deep Neural Networks
Abstract
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.
Cite
@article{arxiv.2101.03263,
title = {SyReNN: A Tool for Analyzing Deep Neural Networks},
author = {Matthew Sotoudeh and Aditya V. Thakur},
journal= {arXiv preprint arXiv:2101.03263},
year = {2021}
}
Comments
Accepted paper at TACAS 2021. Tool is available at https://github.com/95616ARG/SyReNN