Towards an Awareness of Time Series Anomaly Detection Models' Adversarial Vulnerability

TL;DR

This paper reveals that state-of-the-art deep learning models for time series anomaly detection are highly vulnerable to small adversarial perturbations, significantly degrading their performance in real-world scenarios.

Contribution

It is the first to demonstrate the adversarial vulnerabilities of time series anomaly detection models, highlighting the need for robustness in practical applications.

Findings

Performance drops to 0% under FGSM and PGD attacks

Deep neural networks and graph neural networks are vulnerable

Adversarial attacks severely compromise anomaly detection accuracy

Abstract

Time series anomaly detection is extensively studied in statistics, economics, and computer science. Over the years, numerous methods have been proposed for time series anomaly detection using deep learning-based methods. Many of these methods demonstrate state-of-the-art performance on benchmark datasets, giving the false impression that these systems are robust and deployable in many practical and industrial real-world scenarios. In this paper, we demonstrate that the performance of state-of-the-art anomaly detection methods is degraded substantially by adding only small adversarial perturbations to the sensor data. We use different scoring metrics such as prediction errors, anomaly, and classification scores over several public and private datasets ranging from aerospace applications, server machines, to cyber-physical systems in power plants. Under well-known adversarial attacks from Fast Gradient Sign Method (FGSM) and Projected Gradient Descent (PGD) methods, we demonstrate that state-of-the-art deep neural networks (DNNs) and graph neural networks (GNNs) methods, which claim to be robust against anomalies and have been possibly integrated in real-life systems, have their performance drop to as low as 0%. To the best of our understanding, we demonstrate, for the first time, the vulnerabilities of anomaly detection systems against adversarial attacks. The overarching goal of this research is to raise awareness towards the adversarial vulnerabilities of time series anomaly detectors.