Testing Deep Neural Networks

TL;DR

This paper introduces four novel test criteria inspired by MC/DC for evaluating deep neural networks, enabling detection of undesired behaviors with balanced efficiency and effectiveness.

Contribution

The paper proposes a new family of test criteria tailored for DNNs, along with symbolic and gradient-based methods for test case generation, validated on multiple datasets.

Findings

Test criteria effectively detect undesired behaviors in DNNs.

Generated test cases balance bug detection and computational cost.

Validated on MNIST, CIFAR-10, and ImageNet datasets.

Abstract

Deep neural networks (DNNs) have a wide range of applications, and software employing them must be thoroughly tested, especially in safety-critical domains. However, traditional software test coverage metrics cannot be applied directly to DNNs. In this paper, inspired by the MC/DC coverage criterion, we propose a family of four novel test criteria that are tailored to structural features of DNNs and their semantics. We validate the criteria by demonstrating that the generated test inputs guided via our proposed coverage criteria are able to capture undesired behaviours in a DNN. Test cases are generated using a symbolic approach and a gradient-based heuristic search. By comparing them with existing methods, we show that our criteria achieve a balance between their ability to find bugs (proxied using adversarial examples) and the computational cost of test case generation. Our experiments are conducted on state-of-the-art DNNs obtained using popular open source datasets, including MNIST, CIFAR-10 and ImageNet.