PV3 NNRepairrepairs neural network classifiers based on examples

Constraint-based technique to repair neural network classifiers

Application domain/field

Type of tool

Program (neural network) repair

Expected input


Expected output

Repaired neural network.


NNRepair targets neural networks used for classification. First NNrepair uses fault localization to find potentially faulty parameters (weights on edges connecting neurons) in a neural network. Then it performs repair using constraint solving to apply small modifications to the parameters to remedy the defects. The tool is based on NeuroSPF. It uses Symbolic PathFinder and Z3.


A combination of finding a problem (PV1) and suggesting how it can be solved (PV2)
Neural network Program repair


Repository (only contains dataset for experiments of the CAV '21 paper, not the tool itself): https://github.com/muhammadusman93/nnrepair

Related papers

NNrepair: Constraint-Based Repair of Neural Network Classifiers (CAV '21)

Last publication date

15 July 2021

Related tools

ProVerB specific

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