Guiding the Search Towards Failure-Inducing Test Inputs Using Support Vector Machines
In this paper, we present NSGA-II-SVM (Non-dominated Sorting Genetic Algorithm with Support Vector Machine Guidance), a novel learnable evolutionary and search-based testing algorithm that leverages Support Vector Machine (SVM) classification models to direct the search towards failure-revealing test inputs. Supported by genetic search, NSGA-II-SVM creates iteratively SVM-based models of the test input space, learning which regions in the search space are promising to be explored. A subsequent sampling and repetition of evolutionary search iterations allow to refine and make the model more accurate in the prediction. Our preliminary evaluation of NSGA-II-SVM by testing an Automated Valet Parking system shows that NSGA-II-SVM is more effective in identifying more critical test cases than a state of the art learnable evolutionary testing technique as well as naïve random search.
Sat 20 AprDisplayed time zone: Lisbon change
11:00 - 12:30 | Research TalksDeepTest at Eugénio de Andrade Chair(s): Matteo Biagiola Università della Svizzera italiana | ||
11:00 30mPaper | Data vs. Model Machine Learning Fairness Testing: An Empirical Study DeepTest Arumoy Shome Delft University of Technology, Luís Cruz Delft University of Technology, Arie van Deursen Delft University of Technology Pre-print | ||
11:30 30mPaper | Guiding the Search Towards Failure-Inducing Test Inputs Using Support Vector Machines DeepTest Lev Sorokin fortiss GmbH | Technische Universität München, Niklas Kerscher Technische Universität München | Ludwig-Maximilians-Universität München Pre-print | ||
12:00 30mPaper | A Framework for Including Uncertainty in Robustness Evaluation of Bayesian Neural Network Classifiers DeepTest Wasim Essbai Technische Universität Wien, Andrea Bombarda University of Bergamo, Silvia Bonfanti University of Bergamo, Angelo Gargantini University of Bergamo Pre-print | ||