Adversarial Framework with Certified Robustness for Time-Series Domain via Statistical Features

TL;DR

This paper introduces TSA-STAT, a novel adversarial framework for time-series data that uses statistical feature constraints and polynomial transformations to generate effective attacks and certify robustness bounds.

Contribution

It presents a new adversarial attack method tailored for time-series data that employs statistical feature constraints and polynomial transformations, along with certified robustness bounds.

Findings

TSA-STAT effectively fools DNNs on real-world datasets.

The framework provides certified bounds on statistical feature perturbations.

Experimental results demonstrate improved robustness of models against TSA-STAT attacks.

Abstract

Time-series data arises in many real-world applications (e.g., mobile health) and deep neural networks (DNNs) have shown great success in solving them. Despite their success, little is known about their robustness to adversarial attacks. In this paper, we propose a novel adversarial framework referred to as Time-Series Attacks via STATistical Features (TSA-STAT)}. To address the unique challenges of time-series domain, TSA-STAT employs constraints on statistical features of the time-series data to construct adversarial examples. Optimized polynomial transformations are used to create attacks that are more effective (in terms of successfully fooling DNNs) than those based on additive perturbations. We also provide certified bounds on the norm of the statistical features for constructing adversarial examples. Our experiments on diverse real-world benchmark datasets show the effectiveness of TSA-STAT in fooling DNNs for time-series domain and in improving their robustness. The source code of TSA-STAT algorithms is available at https://github.com/tahabelkhouja/Time-Series-Attacks-via-STATistical-Features