Skip to content

Repository files navigation

Framework for Test Dataset Quality Assessment in Deep Neural Networks using various Test Adequacy Criteria and MS

Overview

This framework is used to calculate traiditional test adequacy criteria (Structural and Non-structural), Latent Space Class Dispersion, and Mutation Scores for test dataset quality evaluation. Using this framework, mutant models using pre-training MOs can be trained. Later, LSCD, MS and distance-based Surprise Coverage scores are calculated and their correlation is studied thereby.

Installation

  • Required python version: 3.10
  • OS: Linux, Windows

Create virtual environment

python3.10 -m venv venv

Activate virtual environment

source venv/bin/activate

Install basic requirements

python -m pip install -r requirements.txt

Folder Structure

Data

This folder contains pre-processed datasets that can be used to train mutant models in (/mutagen/).

Dataset

This folder contains dataloading scripts that use base_dataset.py as a base class for loading the MNIST, SVHN, GTSRB and CIFAR-100 datasets. This can be extended to use a new dataset. The "corner_case_dataset.py" file contains a data loader for corner case images from fuzzing.

Models

This folder contains original trained DNN models and their PyTorch implementations.

mutagen

Use this folder and associated files to create mutant models and calculate LSCD, MS, and their correlation using the Pearson Correlation coefficient. A detailed guide can be found in this folder.

Results

This folder should contain results obtained from mutation generation.

Data Availibility

Due to the large size of our corner cases datasets used in our empirical study, we are sharing them via a cloud download link. Please download the necessary files using the following link: https://syncandshare.lrz.de/getlink/fiByBb2QhAViwhFXrjXJfr/

About

Correlation study between various Test Adequacy Metrics and Mutation Score

Resources

Stars

0 stars

Watchers

2 watching

Forks

Releases

Packages

Used by

Contributors

Languages