neural-network-verification

Here are 13 public repositories matching this 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)

neural-networks formal-verification robustness adversarial-examples adversarial-robustness robustness-verification neural-network-verification

Updated Nov 25, 2024
Python

verivital / nnv

Star

Neural Network Verification Software Tool

neural-network verification reachability formal-methods hybrid-systems formal-verification cyber-physical autonomy cyber-physical-systems reachability-analysis robustness-verification trustworthy-machine-learning neural-network-verification trustworthy-ai safe-ai safe-autonomy neural-network-certification assured-autonomy

Updated Nov 26, 2024
MATLAB

Verified-Intelligence / Lyapunov_Stable_NN_Controllers

Star

Lyapunov-stable Neural Control for State and Output Feedback

neural-networks formal-verification neural-control lyapunov-stability neural-network-verification neural-lyapunov-function

Updated Jul 15, 2024
Python

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.

machine-learning symbolic-execution dynamic-analysis program-verification loop-invariants invariant-generation specification-mining neural-network-verification

Updated Sep 5, 2024
Python

samysweb / NCubeV

Star

NCubeV - The Nonlinear Neural Network Verifier

verification smt neural-network-verification

Updated Nov 26, 2024
Jupyter Notebook

ti1uan / simplex-CROWN

Star

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.

neural-network crown robustness adversarial-robustness neural-network-verification

Updated May 3, 2024
Python

phK3 / DPNeurifyFV.jl

Star

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

neural-networks branch-and-bound neural-network-verification

Updated Jul 23, 2024
Julia

AndyVale / residual_benchmarks_vnncomp

Star

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.

neural-network verification neural-networks benchmarks residual-networks residual-neural-networks neural-network-verification vnncomp

Updated Sep 2, 2024

AndyVale / fullyconnected_benchmarks_vnncomp

Star

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.

neural-network verification neural-networks benchmarks fully-connected-network fully-connected-neural-network neural-network-verification vnncomp

Updated Sep 2, 2024

AndyVale / benchmarks_vnncomp

Star

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.

neural-network neural-networks benchmarks residual-network fully-connected-network convolutional-network neural-network-verification vnncomp

Updated Oct 4, 2024
Python

AndyVale / convolutional_benchmarks_vnncomp

Star

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.

neural-network verification neural-networks benchmarks convolutional-networks convolutional-neural-networks neural-network-verification vnncomp