# Importance-Driven Deep Learning System Testing

arXiv: https://arxiv.org/abs/2002.03433 · HTML: https://mlsanity.com/paper/2002.03433/

## Key facts

- Cited by 24 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 9 Feb 2020.

## Built on by (most cited first, 24 of 24)

- [Towards Training Reproducible Deep Learning Models](https://mlsanity.com/paper/2202.02326/) (2022)
- [Black-Box Testing of Deep Neural Networks Through Test Case Diversity](https://mlsanity.com/paper/2112.12591/) (2021)
- [NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks](https://mlsanity.com/paper/2203.12915/) (2022)
- [DeepGD: A Multi-Objective Black-Box Test Selection Approach for Deep Neural Networks](https://mlsanity.com/paper/2303.04878/) (2023)
- [Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction](https://mlsanity.com/paper/2308.09647/) (2023)
- [A Review and Refinement of Surprise Adequacy](https://mlsanity.com/paper/2103.05939/) (2021)
- [Measuring Discrimination to Boost Comparative Testing for Multiple Deep Learning Models](https://mlsanity.com/paper/2103.04333/) (2021)
- [Fairness Testing of Deep Image Classification with Adequacy Metrics](https://mlsanity.com/paper/2111.08856/) (2021)
- [Machine Learning Model Development from a Software Engineering Perspective: A Systematic Literature Review](https://mlsanity.com/paper/2102.07574/) (2021)
- [Keep your Distance: Determining Sampling and Distance Thresholds in Machine Learning Monitoring](https://mlsanity.com/paper/2207.05078/) (2022)
- [Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing](https://mlsanity.com/paper/2307.11011/) (2023)
- [Scope Compliance Uncertainty Estimate](https://mlsanity.com/paper/2312.10801/) (2023)
- [Interpretability-Guided Test-Time Adversarial Defense](https://mlsanity.com/paper/2409.15190/) (2024)
- [Test Where Decisions Matter: Importance-driven Testing for Deep Reinforcement Learning](https://mlsanity.com/paper/2411.07700/) (2024)
- [Guiding the retraining of convolutional neural networks against adversarial inputs](https://mlsanity.com/paper/2207.03689/) (2022)
- [Feature Map Testing for Deep Neural Networks](https://mlsanity.com/paper/2307.11563/) (2023)
- [TraceFL: Interpretability-Driven Debugging in Federated Learning via Neuron Provenance](https://mlsanity.com/paper/2312.13632/) (2023)
- [Neuroevolutionary algorithms driven by neuron coverage metrics for semi-supervised classification](https://mlsanity.com/paper/2303.02801/) (2023)
- [Testing the Channels of Convolutional Neural Networks](https://mlsanity.com/paper/2303.03400/) (2023)
- [DeepKnowledge: Generalisation-Driven Deep Learning Testing](https://mlsanity.com/paper/2403.16768/) (2024)
- [Robust Black-box Testing of Deep Neural Networks using Co-Domain Coverage](https://mlsanity.com/paper/2408.06766/) (2024)
- [LeCov: Multi-level Testing Criteria for Large Language Models](https://mlsanity.com/paper/2408.10474/) (2024)
- [ProToken: Token-Level Attribution for Federated Large Language Models](https://mlsanity.com/paper/2601.19672/) (2026)
- [DDOR: Delta Debugging for Explainable Overrefusal Testing and Repair](https://mlsanity.com/paper/2606.03601/) (2026)

## Abstract (arXiv)

Deep Learning (DL) systems are key enablers for engineering intelligent applications due to their ability to solve complex tasks such as image recognition and machine translation. Nevertheless, using DL systems in safety- and security-critical applications requires to provide testing evidence for their dependable operation. Recent research in this direction focuses on adapting testing criteria from traditional software engineering as a means of increasing confidence for their correct behaviour. However, they are inadequate in capturing the intrinsic properties exhibited by these systems. We bridge this gap by introducing DeepImportance, a systematic testing methodology accompanied by an Importance-Driven (IDC) test adequacy criterion for DL systems. Applying IDC enables to establish a layer-wise functional understanding of the importance of DL system components and use this information to assess the semantic diversity of a test set. Our empirical evaluation on several DL systems, across multiple DL datasets and with state-of-the-art adversarial generation techniques demonstrates the usefulness and effectiveness of DeepImportance and its ability to support the engineering of more robust DL systems.