SyReNN: A Tool for Analyzing Deep Neural Networks

Sotoudeh, Matthew and Thakur, Aditya V.
27th International Conference on Tools and Algorithms for the Construction and Analysis of Systems TACAS, 2021

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.

PDF     Springer©    

@inproceedings{TACAS2021,
  author = {Sotoudeh, Matthew and Thakur, Aditya V.},
  title = {SyReNN: A Tool for Analyzing Deep Neural Networks},
  booktitle = {27th International Conference on Tools and Algorithms for the Construction and Analysis of Systems {TACAS}},
  publisher = {Springer},
  year = {2021},
  doi = {10.1007/978-3-030-72013-1_15}
}