DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems

Abstract

Deep learning (DL) defines a new data-driven programming paradigm that constructs the internal system logic of a crafted neuron network through a set of training data. We have seen wide adoption of DL in many safety-critical scenarios. However, a plethora of studies have shown that the state-of-the-art DL systems suffer from various vulnerabilities which can lead to severe consequences when applied to real-world applications. Currently, the testing adequacy of a DL system is usually measured by the accuracy of test data. Considering the limitation of accessible high quality test data, good accuracy performance on test data can hardly provide confidence to the testing adequacy and generality of DL systems. Unlike traditional software systems that have clear and controllable logic and functionality, the lack of interpretability in a DL system makes system analysis and defect detection difficult, which could potentially hinder its real-world deployment. In this paper, we propose DeepGauge, a set of multi-granularity testing criteria for DL systems, which aims at rendering a multi-faceted portrayal of the testbed. The in-depth evaluation of our proposed testing criteria is demonstrated on two well-known datasets, five DL systems, and with four state-of-the-art adversarial attack techniques against DL. The potential usefulness of DeepGauge sheds light on the construction of more generic and robust DL systems.

The 33rd IEEE/ACM International Conference on Automated Software Engineering (ASE 2018)

References in corpus (2)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• Interpretability Beyond Feature Attribution: Quantitative Testing with Concept Activation Vectors (TCAV)

Cited by in corpus (45)

• Securing Connected & Autonomous Vehicles: Challenges Posed by Adversarial Machine Learning and The Way Forward
• A Performance-Sensitive Malware Detection System Using Deep Learning on Mobile Devices
• How Deep Learning Sees the World: A Survey on Adversarial Attacks & Defenses
• Black-Box Testing of Deep Neural Networks Through Test Case Diversity
• How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
• Boosting Operational DNN Testing Efficiency through Conditioning
• Machine Learning for Software Engineering: A Systematic Mapping
• Arachne: Search Based Repair of Deep Neural Networks
• FDA3 : Federated Defense Against Adversarial Attacks for Cloud-Based IIoT Applications
• METTLE: a METamorphic testing approach to assessing and validating unsupervised machine LEarning systems
• Comparing Offline and Online Testing of Deep Neural Networks: An Autonomous Car Case Study
• A Search-Based Testing Approach for Deep Reinforcement Learning Agents
• Simple Techniques Work Surprisingly Well for Neural Network Test Prioritization and Active Learning (Replicability Study)
• ReluDiff: Differential Verification of Deep Neural Networks
• ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
• Towards Training Reproducible Deep Learning Models
• Coverage Guided Testing for Recurrent Neural Networks
• Understanding Performance Problems in Deep Learning Systems
• Testing DNN Image Classifiers for Confusion & Bias Errors
• DLA: Dense-Layer-Analysis for Adversarial Example Detection
• Increasing the Confidence of Deep Neural Networks by Coverage Analysis
• An Exploratory Study on the Introduction and Removal of Different Types of Technical Debt
• Assessing test artifact quality -- A tertiary study
• Operational Calibration: Debugging Confidence Errors for DNNs in the Field
• Operation is the hardest teacher: estimating DNN accuracy looking for mispredictions
• MultiTest: Physical-Aware Object Insertion for Testing Multi-sensor Fusion Perception Systems
• PatchCensor: Patch Robustness Certification for Transformers via Exhaustive Testing
• DeepCover: Advancing RNN Test Coverage and Online Error Prediction using State Machine Extraction
• EREBA: Black-box Energy Testing of Adaptive Neural Networks
• Finding Deviated Behaviors of the Compressed DNN Models for Image Classifications
• ${\text{A}}^3$: Activation Anomaly Analysis
• Beyond Accuracy: An Empirical Study on Unit Testing in Open-source Deep Learning Projects
• DiverGet: A Search-Based Software Testing Approach for Deep Neural Network Quantization Assessment
• QuanTest: Entanglement-Guided Testing of Quantum Neural Network Systems
• Revisiting Deep Neural Network Test Coverage from the Test Effectiveness Perspective
• Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations
• Metamorphic Testing for Pose Estimation Systems
• TEASMA: A Practical Methodology for Test Adequacy Assessment of Deep Neural Networks
• Targeted Deep Learning System Boundary Testing
• Can Offline Testing of Deep Neural Networks Replace Their Online Testing?
• ROME: Testing Image Captioning Systems via Recursive Object Melting
• Path Analysis for Effective Fault Localization in Deep Neural Networks
• Testing Deep Learning Models: A First Comparative Study of Multiple Testing Techniques
• Toward Efficient Testing of Graph Neural Networks via Test Input Prioritization
• Identifying phase transitions in physical systems with neural networks: a neural architecture search perspective