Adversarial Examples in Deep Learning for Multivariate Time Series Regression

TL;DR

This paper investigates the vulnerability of deep learning models for multivariate time series regression to adversarial examples, demonstrating their susceptibility and potential risks in critical applications like finance and energy.

Contribution

First to explore adversarial attacks on DL MTS regression models, adapting techniques from image classification to reveal their vulnerabilities in safety-critical domains.

Findings

All evaluated models are vulnerable to adversarial attacks.

Adversarial examples are transferable across models.

Attacks could cause catastrophic consequences in critical applications.

Abstract

Multivariate time series (MTS) regression tasks are common in many real-world data mining applications including finance, cybersecurity, energy, healthcare, prognostics, and many others. Due to the tremendous success of deep learning (DL) algorithms in various domains including image recognition and computer vision, researchers started adopting these techniques for solving MTS data mining problems, many of which are targeted for safety-critical and cost-critical applications. Unfortunately, DL algorithms are known for their susceptibility to adversarial examples which also makes the DL regression models for MTS forecasting also vulnerable to those attacks. To the best of our knowledge, no previous work has explored the vulnerability of DL MTS regression models to adversarial time series examples, which is an important step, specifically when the forecasting from such models is used in safety-critical and cost-critical applications. In this work, we leverage existing adversarial attack generation techniques from the image classification domain and craft adversarial multivariate time series examples for three state-of-the-art deep learning regression models, specifically Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), and Gated Recurrent Unit (GRU). We evaluate our study using Google stock and household power consumption dataset. The obtained results show that all the evaluated DL regression models are vulnerable to adversarial attacks, transferable, and thus can lead to catastrophic consequences in safety-critical and cost-critical domains, such as energy and finance.