Testing DNN Image Classifiers for Confusion & Bias Errors

Abstract

Image classifiers are an important component of today's software, from consumer and business applications to safety-critical domains. The advent of Deep Neural Networks (DNNs) is the key catalyst behind such wide-spread success. However, wide adoption comes with serious concerns about the robustness of software systems dependent on DNNs for image classification, as several severe erroneous behaviors have been reported under sensitive and critical circumstances. We argue that developers need to rigorously test their software's image classifiers and delay deployment until acceptable. We present an approach to testing image classifier robustness based on class property violations. We found that many of the reported erroneous cases in popular DNN image classifiers occur because the trained models confuse one class with another or show biases towards some classes over others. These bugs usually violate some class properties of one or more of those classes. Most DNN testing techniques focus on per-image violations, so fail to detect class-level confusions or biases. We developed a testing technique to automatically detect class-based confusion and bias errors in DNN-driven image classification software. We evaluated our implementation, DeepInspect, on several popular image classifiers with precision up to 100% (avg.~72.6%) for confusion errors, and up to 84.3% (avg.~66.8%) for bias errors. DeepInspect found hundreds of classification mistakes in widely-used models, many exposing errors indicating confusion or bias.

References in corpus (5)

• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
• Guiding Deep Learning System Testing using Surprise Adequacy
• Fairness Testing: Testing Software for Discrimination
• Adversarial Sample Detection for Deep Neural Network through Model Mutation Testing

Cited by in corpus (6)

• How to Certify Machine Learning Based Safety-critical Systems? A Systematic Literature Review
• Semantic Robustness of Models of Source Code
• ModelDiff: Testing-Based DNN Similarity Comparison for Model Reuse Detection
• Preemptively Pruning Clever-Hans Strategies in Deep Neural Networks
• Distribution-aware Fairness Test Generation
• Reformulating van Rijsbergen's $F_{\beta }$ metric for weighted binary cross-entropy