ODE guided Neural Data Augmentation Techniques for Time Series Data and its Benefits on Robustness

Abstract

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).

arXiv comment8 pages, 5 figures, International Conference on Machine Learning and Applications

References in corpus (15)

• Efficient Estimation of Word Representations in Vector Space
• Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift
• Sequence to Sequence Learning with Neural Networks
• Explaining and Harnessing Adversarial Examples
• EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks
• Deep learning for time series classification: a review
• Ensemble Adversarial Training: Attacks and Defenses
• Towards Deep Learning Models Resistant to Adversarial Attacks
• Multivariate LSTM-FCNs for Time Series Classification
• YOLO9000: Better, Faster, Stronger
• Robustness May Be at Odds with Accuracy
• Insights into LSTM Fully Convolutional Networks for Time Series Classification
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• Adversarial Examples Are a Natural Consequence of Test Error in Noise
• Data augmentation using synthetic data for time series classification with deep residual networks