Year: 2023
Type: article
Abstract: With the increasing popularity of neural networks, it is also important to make sure that at least some properties can be guaranteed for neural networks, especially if safety is a major concern for their applications. In this work, techniques and tools for formal verification specifically made for neural networks are studied. The tools are top performers in the VNN-COMP 2022, which is a competition specifically for formally verifying neural networks. By providing a neural network model in the ONNX format, and a specification in the VNNLIB format, the tools can find whether there exists a case where the specification is satisfied, given the model. With this result, several properties can be verified for different applications of neural networks.
Author: Sommart, Thanapong
Institution: European Organization for Nuclear Research
Language: English
Subfield: Computational Theory and Mathematics
Field: Computer Science
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W7019170617