TSFool: Crafting High-quality Adversarial Time Series through Multi-objective Optimization to Fool Recurrent Neural Network Classifiers. (arXiv:2209.06388v1 [cs.LG])

Deep neural network (DNN) classifiers are vulnerable to adversarial attacks.
Although the existing gradient-based attacks have achieved good performance in
feed-forward model and image recognition tasks, the extension for time series
classification in the recurrent neural network (RNN) remains a dilemma, because
the cyclical structure of RNN prevents direct model differentiation and the
visual sensitivity to perturbations of time series data challenges the
traditional local optimization objective to minimize perturbation. In this
paper, an efficient and widely applicable approach called …

arxiv classifiers network neural network optimization quality recurrent neural network series time series