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

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.

arXiv commentPart of Proceedings of the 31st ACM International Conference on Information and Knowledge Management (CIKM '22)

References in corpus (17)

• A Survey on Deep Learning in Medical Image Analysis
• Explaining and Harnessing Adversarial Examples
• Intriguing properties of neural networks
• Deep Learning for Anomaly Detection: A Review
• Detecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
• Technical Report on the CleverHans v2.1.0 Adversarial Examples Library
• Improving Black-box Adversarial Attacks with a Transfer-based Prior
• Adversarial Attacks on Deep Neural Networks for Time Series Classification
• DeepRain: ConvLSTM Network for Precipitation Prediction using Multichannel Radar Data
• Defense Against Adversarial Attacks Using Feature Scattering-based Adversarial Training
• TSViz: Demystification of Deep Learning Models for Time-Series Analysis
• One Detector to Rule Them All: Towards a General Deepfake Attack Detection Framework
• Testing Robustness Against Unforeseen Adversaries
• Improving Adversarial Robustness via Channel-wise Activation Suppressing
• Robust Subspace Recovery Layer for Unsupervised Anomaly Detection
• Jacobian Regularization for Mitigating Universal Adversarial Perturbations
• Optimal Transport as a Defense Against Adversarial Attacks

Cited by in corpus (1)

• Boosting Certified Robustness for Time Series Classification with Efficient Self-Ensemble