Wasserstein generative adversarial networks for online test generation for cyber physical systems

Jarkko Peltomäki; Frankie Spencer; Ivan Porres

doi:10.1145/3526072.3527522

Wasserstein generative adversarial networks for online test generation for cyber physical systems

Jarkko Peltomäki, Frankie Spencer, Ivan Porres

Information Technology

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

3 Citations (Scopus)

Abstract

We propose a novel online test generation algorithm WOGAN based on Wasserstein Generative Adversarial Networks. WOGAN is a general-purpose black-box test generator applicable to any system under test having a fitness function for determining failing tests. As a proof of concept, we evaluate WOGAN by generating roads such that a lane assistance system of a car fails to stay on the designated lane. We find that our algorithm has a competitive performance respect to previously published algorithms.

Original language	English
Title of host publication	The 15th Search-Based Software Testing Workshop SBST 2022
Publisher	IEEE
Pages	1-5
ISBN (Print)	978-1-4503-9318-8
DOIs	https://doi.org/10.1145/3526072.3527522
Publication status	Published - 2022
MoE publication type	A4 Article in a conference publication
Event	International Workshop on Search-Based Software Testing - Duration: 9 May 2022 → …

Conference

Conference	International Workshop on Search-Based Software Testing
Abbreviated title	SBST
Period	09/05/22 → …

Access to Document

10.1145/3526072.3527522

http://arxiv.org/abs/2205.11060Licence: Publisher rights policy

Cite this

@inproceedings{aab77bc36f4d4d9a8fe8124f51382db7,

title = "Wasserstein generative adversarial networks for online test generation for cyber physical systems",

abstract = "We propose a novel online test generation algorithm WOGAN based on Wasserstein Generative Adversarial Networks. WOGAN is a general-purpose black-box test generator applicable to any system under test having a fitness function for determining failing tests. As a proof of concept, we evaluate WOGAN by generating roads such that a lane assistance system of a car fails to stay on the designated lane. We find that our algorithm has a competitive performance respect to previously published algorithms.",

author = "Jarkko Peltom{\"a}ki and Frankie Spencer and Ivan Porres",

year = "2022",

doi = "10.1145/3526072.3527522",

language = "English",

isbn = "978-1-4503-9318-8",

pages = "1--5",

booktitle = "The 15th Search-Based Software Testing Workshop SBST 2022",

publisher = "IEEE",

address = "United States",

note = "International Workshop on Search-Based Software Testing, SBST ; Conference date: 09-05-2022",

}

TY - GEN

T1 - Wasserstein generative adversarial networks for online test generation for cyber physical systems

AU - Peltomäki, Jarkko

AU - Spencer, Frankie

AU - Porres, Ivan

PY - 2022

Y1 - 2022

N2 - We propose a novel online test generation algorithm WOGAN based on Wasserstein Generative Adversarial Networks. WOGAN is a general-purpose black-box test generator applicable to any system under test having a fitness function for determining failing tests. As a proof of concept, we evaluate WOGAN by generating roads such that a lane assistance system of a car fails to stay on the designated lane. We find that our algorithm has a competitive performance respect to previously published algorithms.

AB - We propose a novel online test generation algorithm WOGAN based on Wasserstein Generative Adversarial Networks. WOGAN is a general-purpose black-box test generator applicable to any system under test having a fitness function for determining failing tests. As a proof of concept, we evaluate WOGAN by generating roads such that a lane assistance system of a car fails to stay on the designated lane. We find that our algorithm has a competitive performance respect to previously published algorithms.

U2 - 10.1145/3526072.3527522

DO - 10.1145/3526072.3527522

M3 - Conference contribution

SN - 978-1-4503-9318-8

SP - 1

EP - 5

BT - The 15th Search-Based Software Testing Workshop SBST 2022

PB - IEEE

T2 - International Workshop on Search-Based Software Testing

Y2 - 9 May 2022

ER -

Wasserstein generative adversarial networks for online test generation for cyber physical systems

Abstract

Conference

Access to Document

Fingerprint

Cite this