When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study

This repository contains the source code and the data of the paper "When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study" by V. Riccio and P. Tonella, accepted at the 45th IEEE/ACM International Conference on Software Engineering (ICSE 2023).

Reference

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

@inproceedings{tig_validity_ICSE23,
	title= {When and Why Test Generators for Deep Learning Produce Invalid Inputs: an Empirical Study},
	author= {Vincenzo Riccio and Paolo Tonella},
	booktitle= {Proceedings of the 45th IEEE/ACM International Conference on Software Engineering},
	series= {ICSE '23},
	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:

• Vincenzo Riccio (vincenzo.riccio@usi.ch)
• Paolo Tonella (paolo.tonella@usi.ch).