Neuron Sensitivity Guided Test Case Selection for Deep Learning Testing
Not on the map. Why?
Abstract (arXiv)
Deep Neural Networks~(DNNs) have been widely deployed in software to address various tasks~(e.g., autonomous driving, medical diagnosis). However, they could also produce incorrect behaviors that result in financial losses and even threaten human safety. To reveal the incorrect behaviors in DNN and repair them, DNN developers often collect rich unlabeled datasets from the natural world and label them to test the DNN models. However, properly labeling a large number of unlabeled datasets is a highly expensive and time-consuming task. To address the above-mentioned problem, we propose NSS, Neuron Sensitivity guided test case Selection, which can reduce the labeling time by selecting valuable test cases from unlabeled datasets. NSS leverages the internal neuron's information induced by test cases to select valuable test cases, which have high confidence in causing the model to behave incorrectly. We evaluate NSS with four widely used datasets and four well-designed DNN models compared to SOTA baseline methods. The results show that NSS performs well in assessing the test cases' probability of fault triggering and model improvement capabilities. Specifically, compared with baseline approaches, NSS obtains a higher fault detection rate~(e.g., when selecting 5% test case from the unlabeled dataset in MNIST & LeNet1 experiment, NSS can obtain 81.8% fault detection rate, 20% higher than baselines).
Key facts. Cited by 3 papers in the map (data through 14 Oct 2026). Builds on 34 of its 76 references that are in the map. First posted on arXiv 20 Jul 2023.
Builds on
34 of 76 references.
References · 34
- 2015Deep Residual Learning for Image Recognitioncited by 52,096
- 2014Very Deep Convolutional Networks for Large-Scale Image Recognitioncited by 15,364
- 2014Explaining and Harnessing Adversarial Examplescited by 7,364
- 2017Towards Deep Learning Models Resistant to Adversarial Attackscited by 6,415
- 2017Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithmscited by 4,349
- 2016Adversarial examples in the physical worldcited by 1,769
- 2019Theoretically Principled Trade-off between Robustness and Accuracycited by 1,517
- 2016End to End Learning for Self-Driving Carscited by 1,009
- 2015The Limitations of Deep Learning in Adversarial Settingscited by 790
- 2020A Survey of Deep Active Learningcited by 554
- 2013Do Deep Nets Really Need to be Deep?cited by 474
- 2017DeepXplore: Automated Whitebox Testing of Deep Learning Systemscited by 311
22 more
- 2017DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Carscited by 251
- 2021Adversarial Neuron Pruning Purifies Backdoored Deep Modelscited by 235
- 2018DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systemscited by 147
- 2018Guiding Deep Learning System Testing using Surprise Adequacycited by 124
- 2019Neural Machine Translation: A Review and Surveycited by 100
- 2022Improving Adversarial Transferability via Neuron Attribution-Based Attackscited by 93
- 2018DeepMutation: Mutation Testing of Deep Learning Systemscited by 67
- 2019Understanding Neural Networks via Feature Visualization: A surveycited by 65
- 2018Concolic Testing for Deep Neural Networkscited by 51
- 2018Testing Deep Neural Networkscited by 36
- 2022SAFE: Sensitivity-Aware Features for Out-of-Distribution Object Detectioncited by 33
- 2021RobOT: Robustness-Oriented Testing for Deep Learning Systemscited by 28
- 2022Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)cited by 27
- 2020Importance-Driven Deep Learning System Testingcited by 24
- 2019Boosting Operational DNN Testing Efficiency through Conditioningcited by 22
- 2022NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networkscited by 18
- 2020NeuralSens: Sensitivity Analysis of Neural Networkscited by 14
- 2023Adversarial Attacks on the Interpretation of Neuron Activation Maximizationcited by 7
- 2019Interpreting and Improving Adversarial Robustness of Deep Neural Networks with Neuron Sensitivitycited by 6
- 2018DeepHunter: Hunting Deep Neural Network Defects via Coverage-Guided Fuzzingcited by 4
- 2022Machine Learning-based Test Selection for Simulation-based Testing of Self-driving Cars Softwarecited by 3
- 2020One Neuron to Fool Them Allcited by 2
Built on by
Citing papers per year: 2024: 1; 2025: 1; 2026: 1.
3 papers.