TSFool: Crafting Highly-Imperceptible Adversarial Time Series through Multi-Objective Attack

arXiv:2209.06388v3 Announce Type: replace
Abstract: Recent years have witnessed the success of recurrent neural network (RNN) models in time series classification (TSC). However, neural networks (NNs) are vulnerable to adversarial samples, which cause real-life adversarial attacks that undermine the robustness of AI models. To date, most existing attacks target at feed-forward NNs and image recognition tasks, but they cannot perform well on RNN-based TSC. This is due to the cyclical computation of RNN, which prevents direct model differentiation. In addition, …

abstract adversarial adversarial attacks ai models arxiv attacks classification cs.cr cs.lg however life multi-objective network networks neural network neural networks nns recurrent neural network rnn robustness samples series success through time series type undermine vulnerable