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

被引:2
|
作者
Tariq, Shahroz [1 ]
Le, Binh M. [2 ]
Woo, Simon S. [3 ]
机构
[1] Data61 CSIRO, Sydney, NSW, Australia
[2] Sungkyunkwan Univ, Coll Comp & Informat, Seoul, South Korea
[3] Sungkyunkwan Univ, Dept Artificial Intelligence, Seoul, South Korea
基金
新加坡国家研究基金会;
关键词
Adversarial Attack; Anomaly Detection; Time Series; Classification;
D O I
10.1145/3511808.3557073
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
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.
引用
收藏
页码:3534 / 3544
页数:11
相关论文
共 50 条
  • [21] Point-Correlate Adversarial Transformer for Unsupervised Multivariate Time Series Anomaly Detection
    Li, Huan
    Kong, Xiangjie
    Shen, Guojiang
    Yang, Xiaoran
    Yang, Yao
    Collotta, Mario
    PROCEEDINGS OF THE 2024 27 TH INTERNATIONAL CONFERENCE ON COMPUTER SUPPORTED COOPERATIVE WORK IN DESIGN, CSCWD 2024, 2024, : 297 - 302
  • [22] Anomaly Detection for Time Series with Difference Rate Sample Entropy and Generative Adversarial Networks
    Gao, Keke
    Feng, Wenbin
    Zhao, Xia
    Yu, Chongchong
    Su, Weijun
    Niu, Yuqing
    Han, Lu
    COMPLEXITY, 2021, 2021
  • [23] Self-adversarial variational autoencoder with spectral residual for time series anomaly detection
    Liu, Yunxiao
    Lin, Youfang
    Xiao, QinFeng
    Hu, Ganghui
    Wang, Jing
    NEUROCOMPUTING, 2021, 458 (458) : 349 - 363
  • [24] Unsupervised Anomaly Detection Approach Based on Adversarial Memory Autoencoders for Multivariate Time Series
    Zhao, Tianzi
    Jin, Liang
    Zhou, Xiaofeng
    Li, Shuai
    Liu, Shurui
    Zhu, Jiang
    CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 76 (01): : 329 - 346
  • [25] Multivariate time series anomaly detection: A framework of Hidden Markov Models
    Li, Jinbo
    Pedrycz, Witold
    Jamal, Iqbal
    APPLIED SOFT COMPUTING, 2017, 60 : 229 - 240
  • [26] IMDIFFUSION: Imputed Diffusion Models for Multivariate Time Series Anomaly Detection
    Chen, Yuhang
    Zhang, Chaoyun
    Ma, Minghua
    Liu, Yudong
    Ding, Ruomeng
    Li, Bowen
    He, Shilin
    Rajmohan, Saravan
    Lin, Qingwei
    Zhang, Dongmei
    PROCEEDINGS OF THE VLDB ENDOWMENT, 2023, 17 (03): : 359 - 372
  • [27] Time Series Anomaly Detection using Diffusion-based Models
    Pintilie, Ioana
    Manolache, Andrei
    Brad, Florin
    2023 23RD IEEE INTERNATIONAL CONFERENCE ON DATA MINING WORKSHOPS, ICDMW 2023, 2023, : 570 - 578
  • [28] Anomaly Detection at Scale: The Case for Deep Distributional Time Series Models
    Ayed, Fadhel
    Stella, Lorenzo
    Januschowski, Tim
    Gasthaus, Jan
    SERVICE-ORIENTED COMPUTING, ICSOC 2020, 2021, 12632 : 97 - 109
  • [29] Multivariate Time Series Anomaly Detection With Generative Adversarial Networks Based on Active Distortion Transformer
    Kong, Lingkun
    Yu, Jinsong
    Tang, Diyin
    Song, Yue
    Han, Danyang
    IEEE SENSORS JOURNAL, 2023, 23 (09) : 9658 - 9668
  • [30] MAD-GAN: Multivariate Anomaly Detection for Time Series Data with Generative Adversarial Networks
    Li, Dan
    Chen, Dacheng
    Shi, Lei
    Jin, Baihong
    Goh, Jonathan
    Ng, See-Kiong
    ARTIFICIAL NEURAL NETWORKS AND MACHINE LEARNING - ICANN 2019: TEXT AND TIME SERIES, PT IV, 2019, 11730 : 703 - 716