Benchmarking adversarial attacks and defenses for time-series data
This work addresses adversarial vulnerability for time-series data, which is important for applications like finance and healthcare, but it is incremental as it applies existing methods to a new domain.
The paper benchmarks established adversarial defense methods on time-series data under the L∞ threat model, finding that these defenses provide robustness against both white-box and black-box attacks.
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 $L_{\infty}$ 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.