A Noise-Sensitivity-Analysis-Based Test Prioritization Technique for Deep Neural Networks
This work addresses the challenge of improving adversarial testing efficiency for DNNs in domains like image recognition, but it is incremental as it builds on existing noise-based adversarial example generation methods.
The paper tackles the problem of efficiently generating adversarial examples for deep neural networks by proposing a test prioritization technique based on noise sensitivity analysis, showing that examples vary in sensitivity and the method effectively selects them across four image sets and two DNN models.
Deep neural networks (DNNs) have been widely used in the fields such as natural language processing, computer vision and image recognition. But several studies have been shown that deep neural networks can be easily fooled by artificial examples with some perturbations, which are widely known as adversarial examples. Adversarial examples can be used to attack deep neural networks or to improve the robustness of deep neural networks. A common way of generating adversarial examples is to first generate some noises and then add them into original examples. In practice, different examples have different noise-sensitive. To generate an effective adversarial example, it may be necessary to add a lot of noise to low noise-sensitive example, which may make the adversarial example meaningless. In this paper, we propose a noise-sensitivity-analysis-based test prioritization technique to pick out examples by their noise sensitivity. We construct an experiment to validate our approach on four image sets and two DNN models, which shows that examples are sensitive to noise and our method can effectively pick out examples by their noise sensitivity.