neural-network-verification

There are 12 repositories under neural-network-verification topic.

  • Verified-Intelligence/alpha-beta-CROWN

    alpha-beta-CROWN: An Efficient, Scalable and GPU Accelerated Neural Network Verifier (winner of VNN-COMP 2021, 2022, 2023, and 2024)

    Language:Python248147760

  • verivital/nnv

    Neural Network Verification Software Tool

    Language:MATLAB11475849

  • Verified-Intelligence/Lyapunov_Stable_NN_Controllers

    Lyapunov-stable Neural Control for State and Output Feedback

    Language:Python575214
  • dig

    dynaroars/dig

    DIG is a numerical invariant generation tool. It infers program invariants or properties over (i) program execution traces or (ii) program source code. DIG supports many forms of numerical invariants, including nonlinear equalities, octagonal and interval properties, min/max-plus relations, and congruence relations.

    Language:Python395446

  • samysweb/NCubeV

    NCubeV - The Nonlinear Neural Network Verifier

    Language:Jupyter Notebook3100

  • phK3/DPNeurifyFV.jl

    Verification of neural networks based on input splitting and forward propagation of symbolic intervals with fresh variables.

    Language:Julia1201

  • t1u4n/simplex-CROWN

    Uses the simplex to propose a tighter boundary for the l1 perturbation of the convex activation function network, improving the effect of the CROWN algorithm.

    Language:Python1200

  • AndyVale/benchmarks_vnncomp

    A reorganized collection of benchmarks from VNNCOMP since 2022, divided into three categories: fully connected, convolutional, and residual networks. Each category is available as a submodule, allowing you to download individual categories or all of them at once.

    Language:Python

  • AndyVale/convolutional_benchmarks_vnncomp

    This repository contains a collection of convolutional benchmarks from VNNCOMP 2022-2024. It is designed to offer a more organized version of the existing benchmarks, making it easier to test new software. We recommend cloning the 'benchmarks_vnncomp' repository, which includes this repository as a submodule.

  • AndyVale/fullyconnected_benchmarks_vnncomp

    This repository contains a collection of fully connected benchmarks from VNNCOMP 2022-2024. It is designed to offer a more organized version of the existing benchmarks, making it easier to test new software. We recommend cloning the 'benchmarks_vnncomp' repository, which includes this repository as a submodule.

  • AndyVale/residual_benchmarks_vnncomp

    This repository contains a collection of residual benchmarks from VNNCOMP 2022-2024. It is designed to offer a more organized version of the existing benchmarks, making it easier to test new software. We recommend cloning the 'benchmarks_vnncomp' repository, which includes this repository as a submodule.

  • MFHChehade/NN-Verification

    We find the largest region where a given property of a pre-trained neural network is verified.

    Language:Jupyter Notebook10