This repository contains the source code and the data of the paper "DeepHyperion: Exploring the Feature Space of Deep Learning-Based Systems through Illumination Search" by T. Zohdinasab, V. Riccio, A. Gambi and P. Tonella, published in the Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis (ISSTA 2021).

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

Click here to see how to validate the paper’s claims and results in detail. This section introduces also extra use case scenarios to suggest how to extend the code beyond the scope of the paper.

The package is structured as follows:

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

Note: each sub-package contains further specific instructions.

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{DeepHyperion_ISSTA_2021,
	title= {DeepHyperion: Exploring the Feature Space of DeepLearning-Based Systems through Illumination Search},
	author= {Tahereh Zohdinasab and Vincenzo Riccio and Alessio Gambi and Paolo Tonella},
	booktitle= {Proceedings of the ACM SIGSOFT International Symposium on Software Testing and Analysis},
	series= {ISSTA '21},
	publisher= {Association for Computing Machinery},
	year= {2021}
}

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

For any related question, please contact its authors:

• Tahereh Zohdinasab (tahereh.zohdinasab@usi.ch)
• Vincenzo Riccio (vincenzo.riccio@usi.ch)
• Alessio Gambi (alessio.gambi@uni-passau.de)
• Paolo Tonella (paolo.tonella@usi.ch).