SyReNN: a tool for analyzing deep neural networks
From MaRDI portal
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.
Recommendations
- Abstract neural networks
- Reluplex: a calculus for reasoning about deep neural networks
- \textsc{NeVer}: a tool for artificial neural networks verification
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Enhancing robustness verification for deep neural networks via symbolic propagation
Cites work
- Deep learning
- Formal verification of piece-wise linear feed-forward neural networks
- Reluplex: an efficient SMT solver for verifying deep neural networks
- Safety verification of deep neural networks
- Tools and algorithms for the construction and analysis of systems. 22nd international conference, TACAS 2016, held as part of the European joint conferences on theory and practice of software, ETAPS 2016, Eindhoven, The Netherlands, April 2--8, 2016. Proc
Describes a project that uses
Uses Software
This page was built for publication: SyReNN: a tool for analyzing deep neural networks
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2233513)
