VNN-LIB

The international benchmarks standard for the Verification of Neural Networks

Highlights

ONNX

Networks

An open format built to represent machine learning models.

SMT-LIB

Properties

An international initiative aimed at facilitating research and development in Satisfiability Modulo Theories (SMT).

CoCoNet

Tool

A tool for construction and conversion of neural networks across different standards.

Benchmarks

Benchmarks

Our benchmarks repository from current research case studies.

VNN-COMP 2023

Benchmarks

The benchmarks repository of the VNN competition - 2023.

Issue Tracker

Contribution

Repository for submitting issues and start discussions about VNN-LIB.

Standard

The VNN-LIB standard - version 1.0.
This document refers to the paper presented at FoMLAS 2023: S. Demarchi, D. Guidotti, L. Pulina and A. Tacchella,
Supporting Standardization of Neural Networks Verification with VNN-LIB and CoCoNet



Team

...

Armando Tacchella

Full Professor | UniGE

...

Luca Pulina

Full Professor | UniSS

...

Dario Guidotti

Post-Doc Researcher | UniSS

...

Stefano Demarchi

Post-Doc Researcher | UniGE