pyNeVer

Neural networks Verifier (NeVer 2) is a tool for the training, pruning and verification of neural networks. At present it supports sequential fully connected neural networks with ReLU and Sigmoid activation functions. pyNeVer is the corresponding python package providing all the main capabilities of the NeVer 2 tool and can be easily installed using pip. The PyPI project page can be found at https://pypi.org/project/pyNeVer/ whereas the github repository can be found at https://github.com/NeVerTools/pyNeVer.

REQUIREMENTS AND INSTALLATION

pyNeVer depends on several packages, which should be installed automatically. The packages required for the correct execution are the following:

• numpy
• ortools
• onnx
• torch
• torchvision
• pysmt

All the above packages are available via pip.

To install pyNeVer, run the command:

pip install pynever

To run some examples, further packages may be required. If an example requires a specific package, it will be detailed in the example directory.

DOCUMENTATION

The documentation related to the pyNeVer package can be found in the directory docs/pynever/ as html files.

SUPPORTED INPUTS

At present the pyNeVer package supports only the abstraction and verification of fully connected neural networks with ReLU and Sigmoid activation functions. The training, pruning and conversion supports also batch normalization layers. A network with batchnorm layers following fully connected layers can be converted to a "pure" fully connected neural networks using the capabilities provided in the utilities.py module.
The conversion.py provides the capabilities for the conversion of PyTorch and ONNX networks: therefore this kind of networks can be loaded using the respective frameworks and then converted to the internal representation used by pyNeVer. The properties for the verification and abstraction of the networks must be defined either in python code following the specification which can be found in the documentation, or via an SMT-LIB file compliant to the VNN-LIB standard.

EXAMPLES

NB: All the scripts should be executed INSIDE the related directory!

All the examples described below are guaranteed to work until Release v0.1.1a4. After this release, changes in the interface structure may add inconsistencies between test scripts and API, so the old examples will be removed and new examples will be created in future releases.

• The directory examples/ contains some examples of application of the pyNeVer package. In particular the jupyter notebook shows a graphical example of the application of the abstraction module for the reachability of a small network with bi-dimensional input and outputs.

• The pruning_example.py script show how to train and prune some small fully connected neural networks with relu activation function. It also show how it is possible to combine batch norm layer and fully connected layers to make the networks compliant with the requirements of the verification and abstraction modules.

• The directory examples/submissions/ATVA2021 contains the experimental setup used for the experimental evaluation in our ATVA2021 paper. The experiments can be easily replicated by executing the python scripts acas_experiment.py from within the ATVA2021/ directory. The log files will be generated and will be saved in the logs/ directory.

CONTRIBUTORS

The main contributors of pyNeVer are Dario Guidotti and Armando Tacchella, further contributions are provided by Stefano Demarchi.

Students contributions:

• Alessandro Drago - TensorFlow conversion
• Andrea Gimelli - Bound propagation integration
• Pedro Henrique Simão Achete - Command-line interface