PV1 DLV: Deep Learning Verificationverifies that a neural network has no misclassifications

Framework for automated verification of safety of classification decisions made by feed-forward deep neural networks.

Application domain/field

Expected input

Format:

Everything seems to be defined within a python file.

Expected output

The network is verified (i.e. no misclassifications were found for all layers) or it is falsified (i.e. the tool found an adversarial example )

Internals

Uses Z3, Keras (neural network library), Theano (deep learning package).

Comments

License: GNU General Public License v3.0
DNN Neural network Python

Links

Repository: https://github.com/verideep/dlv

Related papers

Safety Verification of Deep Neural Networks (CAV '17)

Last publication date

13 July 2017

ProVerB specific



ProVerB is a part of SLEBoK. Last updated: February 2023.