SyReNN: A Tool for Analyzing Deep Neural Networks

Matthew Sotoudeh*, Zhe Tao*, and Aditya V. Thakur
*Equal contribution

International Journal on Software Tools for Technology Transfer (STTT) 25(2), 2023

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 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 repairing buggy DNNs.

@article{STTT2023,
  author = {Sotoudeh, Matthew and Tao, Zhe and Thakur, Aditya V.},
  title = {SyReNN: A Tool for Analyzing Deep Neural Networks},
  journal = {International Journal on Software Tools for Technology Transfer {(STTT)}},
  volume = {25},
  number = {2},
  pages = {145--165},
  publisher = {Springer},
  year = {2023},
  doi = {10.1007/s10009-023-00695-1}
}

Back to Publications