Online GANs for Automatic Performance Testing

Ivan Porres; Hergys Rexha; Sébastien Lafond

doi:10.1109/ICSTW52544.2021.00027

Online GANs for Automatic Performance Testing

Ivan Porres, Hergys Rexha, Sébastien Lafond

Information Technology

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

6 Citations (Scopus)

Abstract

In this paper we present a novel algorithm for automatic performance testing that uses an online variant of the Generative Adversarial Network (GAN) to optimize the test generation process. The objective of the proposed approach is to generate, for a given test budget, a test suite containing a high number of tests revealing performance defects. This is achieved using a GAN to generate the tests and predict their outcome. This GAN is trained online while generating and executing the tests. The proposed approach does not require a prior training set or model of the system under test. We provide an initial evaluation the algorithm using an example test system, and compare the obtained results with other possible approaches.We consider that the presented algorithm serves as a proof of concept and we hope that it can spark a research discussion on the application of GANs to test generation.

Original language	English
Title of host publication	Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021
Publisher	IEEE
Pages	95-100
ISBN (Electronic)	9781665444569
ISBN (Print)	978-1-6654-4457-6
DOIs	https://doi.org/10.1109/ICSTW52544.2021.00027
Publication status	Published - Apr 2021
MoE publication type	A4 Article in a conference publication
Event	IEEE International Conference on Software Testing Verification and Validation Workshop - Duration: 12 Apr 2021 → 16 Apr 2021

Publication series

Name	Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021

Conference

Conference	IEEE International Conference on Software Testing Verification and Validation Workshop
Abbreviated title	ICSTW
Period	12/04/21 → 16/04/21

UN SDGs

This output contributes to the following UN Sustainable Development Goals (SDGs)

Access to Document

10.1109/ICSTW52544.2021.00027

https://dblp.org/rec/conf/icst/PorresRL21

AIDOaRT
Porres Paltor, I. (Principal Investigator), Truscan, D. (Co-Principal Investigator), Nybom, K. (Co-Investigator) & Logacheva, E. (Co-Investigator)
European Commission
01/04/21 → 30/09/24
Project: EU

Cite this

Porres, I., Rexha, H., & Lafond, S. (2021). Online GANs for Automatic Performance Testing. In Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021 (pp. 95-100). Article 9440165 (Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021). IEEE. https://doi.org/10.1109/ICSTW52544.2021.00027

Porres, Ivan ; Rexha, Hergys ; Lafond, Sébastien. / Online GANs for Automatic Performance Testing. Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021. IEEE, 2021. pp. 95-100 (Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021).

@inproceedings{4380f3a6650f40b7ad9e3515ad0960e6,

title = "Online GANs for Automatic Performance Testing",

abstract = "In this paper we present a novel algorithm for automatic performance testing that uses an online variant of the Generative Adversarial Network (GAN) to optimize the test generation process. The objective of the proposed approach is to generate, for a given test budget, a test suite containing a high number of tests revealing performance defects. This is achieved using a GAN to generate the tests and predict their outcome. This GAN is trained online while generating and executing the tests. The proposed approach does not require a prior training set or model of the system under test. We provide an initial evaluation the algorithm using an example test system, and compare the obtained results with other possible approaches.We consider that the presented algorithm serves as a proof of concept and we hope that it can spark a research discussion on the application of GANs to test generation.",

author = "Ivan Porres and Hergys Rexha and S{\'e}bastien Lafond",

note = "https://conferences.ieeeauthorcenter.ieee.org/author-ethics/guidelines-and-policies/post-publication-policies/ accepted paper, embargo 24 m{\aa}n; IEEE International Conference on Software Testing Verification and Validation Workshop, ICSTW ; Conference date: 12-04-2021 Through 16-04-2021",

year = "2021",

month = apr,

doi = "10.1109/ICSTW52544.2021.00027",

language = "English",

isbn = "978-1-6654-4457-6",

series = "Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021",

publisher = "IEEE",

pages = "95--100",

booktitle = "Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021",

address = "United States",

}

Porres, I , Rexha, H & Lafond, S 2021, Online GANs for Automatic Performance Testing. in Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021., 9440165, Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021, IEEE, pp. 95-100, IEEE International Conference on Software Testing Verification and Validation Workshop, 12/04/21. https://doi.org/10.1109/ICSTW52544.2021.00027

Online GANs for Automatic Performance Testing. / Porres, Ivan ; Rexha, Hergys ; Lafond, Sébastien.
Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021. IEEE, 2021. p. 95-100 9440165 (Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021).

Research output: Chapter in Book/Conference proceeding › Conference contribution › Scientific › peer-review

TY - GEN

T1 - Online GANs for Automatic Performance Testing

AU - Porres, Ivan

AU - Rexha, Hergys

AU - Lafond, Sébastien

N1 - https://conferences.ieeeauthorcenter.ieee.org/author-ethics/guidelines-and-policies/post-publication-policies/ accepted paper, embargo 24 mån

PY - 2021/4

Y1 - 2021/4

N2 - In this paper we present a novel algorithm for automatic performance testing that uses an online variant of the Generative Adversarial Network (GAN) to optimize the test generation process. The objective of the proposed approach is to generate, for a given test budget, a test suite containing a high number of tests revealing performance defects. This is achieved using a GAN to generate the tests and predict their outcome. This GAN is trained online while generating and executing the tests. The proposed approach does not require a prior training set or model of the system under test. We provide an initial evaluation the algorithm using an example test system, and compare the obtained results with other possible approaches.We consider that the presented algorithm serves as a proof of concept and we hope that it can spark a research discussion on the application of GANs to test generation.

AB - In this paper we present a novel algorithm for automatic performance testing that uses an online variant of the Generative Adversarial Network (GAN) to optimize the test generation process. The objective of the proposed approach is to generate, for a given test budget, a test suite containing a high number of tests revealing performance defects. This is achieved using a GAN to generate the tests and predict their outcome. This GAN is trained online while generating and executing the tests. The proposed approach does not require a prior training set or model of the system under test. We provide an initial evaluation the algorithm using an example test system, and compare the obtained results with other possible approaches.We consider that the presented algorithm serves as a proof of concept and we hope that it can spark a research discussion on the application of GANs to test generation.

U2 - 10.1109/ICSTW52544.2021.00027

DO - 10.1109/ICSTW52544.2021.00027

M3 - Conference contribution

SN - 978-1-6654-4457-6

T3 - Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021

SP - 95

EP - 100

BT - Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021

PB - IEEE

T2 - IEEE International Conference on Software Testing Verification and Validation Workshop

Y2 - 12 April 2021 through 16 April 2021

ER -

Porres I , Rexha H , Lafond S. Online GANs for Automatic Performance Testing. In Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021. IEEE. 2021. p. 95-100. 9440165. (Proceedings - 2021 IEEE 14th International Conference on Software Testing, Verification and Validation Workshops, ICSTW 2021). doi: 10.1109/ICSTW52544.2021.00027

Online GANs for Automatic Performance Testing

Abstract

Publication series

Conference

UN SDGs

Access to Document

Fingerprint

Projects

AIDOaRT

Cite this