# Path Analysis for Effective Fault Localization in Deep Neural Networks

arXiv: https://arxiv.org/abs/2310.18987 · HTML: https://mlsanity.com/paper/2310.18987/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 29 of its 73 references that are in the map.
- First posted on arXiv 29 Oct 2023.

## Builds on (most cited first, 29 of 29)

- [Fashion-MNIST: a Novel Image Dataset for Benchmarking Machine Learning Algorithms](https://mlsanity.com/paper/1708.07747/) (2017)
- [Improved Techniques for Training GANs](https://mlsanity.com/paper/1606.03498/) (2016)
- [Deep Inside Convolutional Networks: Visualising Image Classification Models and Saliency Maps](https://mlsanity.com/paper/1312.6034/) (2013)
- [Importance Estimation for Neural Network Pruning](https://mlsanity.com/paper/1906.10771/) (2019)
- [Understanding Neural Networks Through Deep Visualization](https://mlsanity.com/paper/1506.06579/) (2015)
- [DeepXplore: Automated Whitebox Testing of Deep Learning Systems](https://mlsanity.com/paper/1705.06640/) (2017)
- [DeepTest: Automated Testing of Deep-Neural-Network-driven Autonomous Cars](https://mlsanity.com/paper/1708.08559/) (2017)
- [Machine Learning Testing: Survey, Landscapes and Horizons](https://mlsanity.com/paper/1906.10742/) (2019)
- [Neural Trojans](https://mlsanity.com/paper/1710.00942/) (2017)
- [DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems](https://mlsanity.com/paper/1803.07519/) (2018)
- [Visualizing Deep Convolutional Neural Networks Using Natural Pre-Images](https://mlsanity.com/paper/1512.02017/) (2015)
- [A Primer on Neural Network Models for Natural Language Processing](https://mlsanity.com/paper/1510.00726/) (2015)
- ["What is Relevant in a Text Document?": An Interpretable Machine Learning Approach](https://mlsanity.com/paper/1612.07843/) (2016)
- [On Testing Machine Learning Programs](https://mlsanity.com/paper/1812.02257/) (2018)
- [Causality-based Neural Network Repair](https://mlsanity.com/paper/2204.09274/) (2022)
- [DeepLocalize: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/2103.03376/) (2021)
- [Testing Deep Neural Networks](https://mlsanity.com/paper/1803.04792/) (2018)
- [DeepFault: Fault Localization for Deep Neural Networks](https://mlsanity.com/paper/1902.05974/) (2019)
- [Arachne: Search Based Repair of Deep Neural Networks](https://mlsanity.com/paper/1912.12463/) (2019)
- [NNrepair: Constraint-based Repair of Neural Network Classifiers](https://mlsanity.com/paper/2103.12535/) (2021)
- [DeepDiagnosis: Automatically Diagnosing Faults and Recommending Actionable Fixes in Deep Learning Programs](https://mlsanity.com/paper/2112.04036/) (2021)
- [NPC: Neuron Path Coverage via Characterizing Decision Logic of Deep Neural Networks](https://mlsanity.com/paper/2203.12915/) (2022)
- [DeepFD: Automated Fault Diagnosis and Localization for Deep Learning Programs](https://mlsanity.com/paper/2205.01938/) (2022)
- [DeepRoad: GAN-based Metamorphic Autonomous Driving System Testing](https://mlsanity.com/paper/1802.02295/) (2018)
- [Automatic Fault Detection for Deep Learning Programs Using Graph Transformations](https://mlsanity.com/paper/2105.08095/) (2021)
- [ArchRepair: Block-Level Architecture-Oriented Repairing for Deep Neural Networks](https://mlsanity.com/paper/2111.13330/) (2021)
- [Mutation-based Fault Localization of Deep Neural Networks](https://mlsanity.com/paper/2309.05067/) (2023)
- [Repairing Deep Neural Networks Based on Behavior Imitation](https://mlsanity.com/paper/2305.03365/) (2023)
- [An Effective Data-Driven Approach for Localizing Deep Learning Faults](https://mlsanity.com/paper/2307.08947/) (2023)

## Abstract (arXiv)

Deep learning has revolutionized numerous fields, yet the reliability of Deep Neural Networks (DNNs) remains a concern due to their complexity and data dependency. Traditional software fault localization methods, such as Spectrum-based Fault Localization (SBFL), have been adapted for DNNs but often fall short in effectiveness. These methods typically overlook the propagation of faults through neural pathways, resulting in less precise fault detection. Research indicates that examining neural pathways, rather than individual neurons, is crucial because issues in one neuron can affect its entire pathway. By investigating these interconnected pathways, we can better identify and address problems arising from the collective activity of neurons. To address this limitation, we introduce the NP-SBFL method, which leverages Layer-wise Relevance Propagation (LRP) to identify essential faulty neural pathways. Our method explores multiple fault sources to accurately pinpoint faulty neurons by analyzing their interconnections. Additionally, our multi-stage gradient ascent (MGA) technique, an extension of gradient ascent (GA), enables sequential neuron activation to enhance fault detection. We evaluated NP-SBFL-MGA on the well-established MNIST and CIFAR-10 datasets, comparing it to other methods like DeepFault and NP-SBFL-GA, as well as three neuron measures: Tarantula, Ochiai, and Barinel. Our evaluation utilized all training and test samples (60,000 for MNIST and 50,000 for CIFAR-10) and revealed that NP-SBFL-MGA significantly outperformed the baselines in identifying suspicious pathways and generating adversarial inputs. Notably, Tarantula with NP-SBFL-MGA achieved a remarkable 96.75% fault detection rate compared to DeepFault's 89.90%. NP-SBFL-MGA highlights a strong correlation between critical path coverage and the number of failed tests in DNN fault localization.