Coverage-Guided Testing for Deep Learning Models: A Comprehensive Survey

TL;DR

This comprehensive survey reviews coverage-guided testing methods for deep learning models, analyzing their techniques, evaluation practices, challenges, and future directions to improve model reliability in safety-critical applications.

Contribution

It provides a detailed taxonomy of CGT methods, evaluates current evaluation practices, and highlights open challenges and future research directions in DL model testing.

Findings

Coverage-guided testing is increasingly used for DL model validation.

Existing studies are methodologically fragmented, limiting comprehensive understanding.

Open challenges include correlating structural coverage with testing objectives.

Abstract

As Deep Learning (DL) models are increasingly applied in safety-critical domains, ensuring their quality has emerged as a pressing challenge in modern software engineering. Among emerging validation paradigms, coverage-guided testing (CGT) has gained prominence as a systematic framework for identifying erroneous or unexpected model behaviors. Despite growing research attention, existing CGT studies remain methodologically fragmented, limiting the understanding of current advances and emerging trends. This work addresses that gap through a comprehensive review of state-of-the-art CGT methods for DL models, including test coverage analysis, coverage-guided test input generation, and coverage-guided test input optimization. This work provides detailed taxonomies to organize these methods based on methodological characteristics and application scenarios. We also investigate evaluation practices adopted in existing studies, including the use of benchmark datasets, model architectures, and evaluation aspects. Finally, open challenges and future directions are highlighted in terms of the correlation between structural coverage and testing objectives, method generalizability across tasks and models, practical deployment concerns, and the need for standardized evaluation and tool support. This work aims to provide a roadmap for future academic research and engineering practice in DL model quality assurance.