Revisiting "Revisiting Neuron Coverage for DNN Testing: A Layer-Wise and Distribution-Aware Criterion": A Critical Review and Implications on DNN Coverage Testing

TL;DR

This paper critically reviews the Neural Coverage (NLC) criterion for DNN testing, highlighting its theoretical and empirical limitations, and proposes improvements to enhance the validity and effectiveness of coverage metrics.

Contribution

It provides a thorough critique of NLC, identifies key assumptions and limitations, and suggests directions for developing more robust DNN coverage criteria.

Findings

NLC deviates from core coverage principles like monotonicity.

Empirical study validity is threatened by test suite ordering issues.

Proposed improvements address covariance matrix properties and test suite validity.

Abstract

We present a critical review of Neural Coverage (NLC), a state-of-the-art DNN coverage criterion by Yuan et al. at ICSE 2023. While NLC proposes to satisfy eight design requirements and demonstrates strong empirical performance, we question some of their theoretical and empirical assumptions. We observe that NLC deviates from core principles of coverage criteria, such as monotonicity and test suite order independence, and could more fully account for key properties of the covariance matrix. Additionally, we note threats to the validity of the empirical study, related to the ground truth ordering of test suites. Through our empirical validation, we substantiate our claims and propose improvements for future DNN coverage metrics. Finally, we conclude by discussing the implications of these insights.