论文标题
基于时间扭曲的动态时间扭曲框架的时间序列域
Dynamic Time Warping based Adversarial Framework for Time-Series Domain
论文作者
论文摘要
尽管深度神经网络（DNN）的对抗性鲁棒性的研究取得了迅速的进展，但时间序列领域几乎没有原则上的工作。由于时间序列数据出现在包括移动健康，金融和智能电网在内的各种应用中，因此验证和改善DNN在时间序列域的鲁棒性很重要。在本文中，我们为时间序列域提出了一个新颖的框架，称为{\ em动态时间扭曲，用于使用动态时间扭曲度量的对抗性鲁棒性（dtw-ar）}。提供了理论和经验证据，以证明DTW对图像结构域的先前方法中使用的标准欧几里得距离度量的有效性。我们通过理论分析开发了一种原则性的算法，可以使用随机比对路径有效地创建各种对抗性示例。对不同现实世界基准的实验表明，DTW-AR对愚弄DNNS的有效性来获取时间序列数据，并使用对抗性训练提高其鲁棒性。 DTW-AR算法的源代码可在https://github.com/tahabelkhouja/dtw-ar上获得
Despite the rapid progress on research in adversarial robustness of deep neural networks (DNNs), there is little principled work for the time-series domain. Since time-series data arises in diverse applications including mobile health, finance, and smart grid, it is important to verify and improve the robustness of DNNs for the time-series domain. In this paper, we propose a novel framework for the time-series domain referred as {\em Dynamic Time Warping for Adversarial Robustness (DTW-AR)} using the dynamic time warping measure. Theoretical and empirical evidence is provided to demonstrate the effectiveness of DTW over the standard Euclidean distance metric employed in prior methods for the image domain. We develop a principled algorithm justified by theoretical analysis to efficiently create diverse adversarial examples using random alignment paths. Experiments on diverse real-world benchmarks show the effectiveness of DTW-AR to fool DNNs for time-series data and to improve their robustness using adversarial training. The source code of DTW-AR algorithms is available at https://github.com/tahabelkhouja/DTW-AR
