Semantic Feature-Based Test Selection for Deep Neural Networks: A Frequency Domain Perspective

Zhouxian Jiang1, Honghui Li1, Xuetao Tian2 and Rui Wang1

  1. School of Computing and Information Technology, Beijing Jiaotong University, Beijing, China
  2. Faculty of Psychology, Beijing Normal University, Beijing, China

Abstract

While deep neural networks (DNNs) have great potential for applications in security and safety-critical domains, their limited robustness to adversarial samples and out-of-distribution (OOD) samples raise significant concerns. In the software engineering community, significant efforts have been devoted to devising testing techniques that verify the robustness of DNNs. This paper investigates semantic feature-based test selection for DNNs from a frequency domain perspective and propose a novel method called SaFeTS. Specifically, we leverage saliency detection techniques, such as Fourier Phase Transform to extract semantic features from test cases. These features are then clustered to select diverse test cases to evaluate the robustness of DNNs and model retraining. Experiments on CIFAR-10 and SVHN datasets demonstrate that SaFeTS exposes more varied model errors compared to baseline methods. Further, retraining with SaFeTS-selected samples significantly improves adversarial and out-of-distribution robustness over state-of-the-art test selection methods.

Key words

DNN testing, test selection, semantic feature, frequency domain, robustness

Digital Object Identifier (DOI)

https://doi.org/10.2298/CSIS230907045J

Publication information

Volume 21, Issue 4 (September 2024)
Year of Publication: 2024
ISSN: 2406-1018 (Online)
Publisher: ComSIS Consortium

Full text

DownloadAvailable in PDF
Portable Document Format

How to cite

Jiang, Z., Li, H., Tian, X., Wang, R.: Semantic Feature-Based Test Selection for Deep Neural Networks: A Frequency Domain Perspective. Computer Science and Information Systems, Vol. 21, No. 4, 1499–1522. (2024), https://doi.org/10.2298/CSIS230907045J