Benchmarking adversarial attacks and defenses for time-series data

Authors: Shoaib Ahmed Siddiqui, Andreas Dengel, Sheraz Ahmed
Published: 2020-08-30

Source: https://arxiv.org/abs/2008.13261

PDF: https://arxiv.org/pdf/2008.13261

AIにより推定されたラベル

敵対的攻撃 敵対的サンプル 深層学習技術

※ こちらのラベルはAIによって自動的に追加されました。そのため、正確でないことがあります。
詳細は文献データベースについてをご覧ください。

Abstract

The adversarial vulnerability of deep networks has spurred the interest of researchers worldwide. Unsurprisingly, like images, adversarial examples also translate to time-series data as they are an inherent weakness of the model itself rather than the modality. Several attempts have been made to defend against these adversarial attacks, particularly for the visual modality. In this paper, we perform detailed benchmarking of well-proven adversarial defense methodologies on time-series data. We restrict ourselves to the L_∞ threat model. We also explore the trade-off between smoothness and clean accuracy for regularization-based defenses to better understand the trade-offs that they offer. Our analysis shows that the explored adversarial defenses offer robustness against both strong white-box as well as black-box attacks. This paves the way for future research in the direction of adversarial attacks and defenses, particularly for time-series data.