ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness
This addresses the problem of adversarial robustness for time series data, which has received less attention than images, but the approach is incremental as it builds on existing augmentation methods.
The paper tackled the vulnerability of deep learning time series classifiers to adversarial attacks by introducing two local gradient-based and one spectral density-based data augmentation techniques, resulting in state-of-the-art classification accuracy on benchmarks and improved robustness against common corruption methods like FGSM and BIM.
Exploring adversarial attack vectors and studying their effects on machine learning algorithms has been of interest to researchers. Deep neural networks working with time series data have received lesser interest compared to their image counterparts in this context. In a recent finding, it has been revealed that current state-of-the-art deep learning time series classifiers are vulnerable to adversarial attacks. In this paper, we introduce two local gradient based and one spectral density based time series data augmentation techniques. We show that a model trained with data obtained using our techniques obtains state-of-the-art classification accuracy on various time series benchmarks. In addition, it improves the robustness of the model against some of the most common corruption techniques,such as Fast Gradient Sign Method (FGSM) and Basic Iterative Method (BIM).