DeepAtash

General Information

This repository contains the source code and the data of the paper "DeepAtash: Focused Test Generation for Deep Learning systems" by T. Zohdinasab, V. Riccio, and P. Tonella. published in the Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2023).

Getting Started

Click here to see how to set up DeepAtash and validate its general functionality by using our pre-configured Docker image.

Detailed Description

Click here to see how to validate the paper’s claims and results in detail.

Repository Structure

The package is structured as follows:

• MNIST contains the DeepAtash tool adapted to the handwritten digit classification case study and the instructions on how to use it;
• IMDB contains the DeepAtash tool adapted to the movie sentiment analysis case study and the instructions on how to use it;
• BNG contains the DeepAtash tool adapted to the self-driving car case study and the instructions on how to use it;
• experiments contains the raw experimental data and the scripts to obtain the results reported in the ISSTA paper;
• documentation contains a quick installation guide and a detailed description of the tool.

Note: each sub-package contains further specific instructions.

Reference

If you use our work in your research, or it helps it, or if you simply like it, please cite DeepHyperion in your publications. Here is an example BibTeX entry:

@inproceedings{tahereh2023deepatash,
  title={DeepAtash: Focused Test Generation for Deep Learning Systems},
  author={Tahereh, Zohdinasab and Riccio, Vincenzo and Paolo, Tonella and others},
  booktitle={Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis},
  year={2023}
}

License

The software we developed is distributed under MIT license. See the license file.

Contacts

For any related question, please contact its authors:

• Tahereh Zohdinasab ([email protected])
• Vincenzo Riccio ([email protected])
• Paolo Tonella ([email protected]).

DOI