Testing Deep Learning Models for Image Analysis Using Object-Relevant Metamorphic Relations

Abstract

Deep learning models are widely used for image analysis. While they offer high performance in terms of accuracy, people are concerned about if these models inappropriately make inferences using irrelevant features that are not encoded from the target object in a given image. To address the concern, we propose a metamorphic testing approach that assesses if a given inference is made based on irrelevant features. Specifically, we propose two novel metamorphic relations to detect such inappropriate inferences. We applied our approach to 10 image classification models and 10 object detection models, with three large datasets, i.e., ImageNet, COCO, and Pascal VOC. Over 5.3% of the top-5 correct predictions made by the image classification models are subject to inappropriate inferences using irrelevant features. The corresponding rate for the object detection models is over 8.5%. Based on the findings, we further designed a new image generation strategy that can effectively attack existing models. Comparing with a baseline approach, our strategy can double the success rate of attacks.

Please note that a later version of this paper is accepted by Empirical Software Engineering in 2021. The title of the accepted paper is: "To What Extent Do DNN-based Image Classification Models Make Unreliable Inferences?". Please contact the first author if you are interested in the accepted version

References in corpus (10)

• Very Deep Convolutional Networks for Large-Scale Image Recognition
• YOLOv3: An Incremental Improvement
• DeepXplore: Automated Whitebox Testing of Deep Learning Systems
• DeepGauge: Multi-Granularity Testing Criteria for Deep Learning Systems
• Metamorphic Testing: A New Approach for Generating Next Test Cases
• Identifying Implementation Bugs in Machine Learning based Image Classifiers using Metamorphic Testing
• CornerNet-Lite: Efficient Keypoint Based Object Detection
• Bag of Freebies for Training Object Detection Neural Networks
• Bag of Tricks for Image Classification with Convolutional Neural Networks
• TensorFuzz: Debugging Neural Networks with Coverage-Guided Fuzzing

Cited by in corpus (2)

• Exposing Previously Undetectable Faults in Deep Neural Networks
• Attack as Defense: Characterizing Adversarial Examples using Robustness