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

被引:4
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
来源
PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON INFORMATION AND KNOWLEDGE MANAGEMENT, CIKM 2022 | 2022年
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
[41]   NLP Based Anomaly Detection for Categorical Time Series [J].
Horak, Matthew ;
Chandrasekaran, Sowmya ;
Tobar, Giovanni .
2022 IEEE 23RD INTERNATIONAL CONFERENCE ON INFORMATION REUSE AND INTEGRATION FOR DATA SCIENCE (IRI 2022), 2022, :27-34
[42]   A Review on Outlier/Anomaly Detection in Time Series Data [J].
Blazquez-Garcia, Ane ;
Conde, Angel ;
Mori, Usue ;
Lozano, Jose A. .
ACM COMPUTING SURVEYS, 2022, 54 (03)
[43]   Anomaly Detection from Time Series Under Uncertainty [J].
Wiessner, Paul ;
Bezirganyan, Grigor ;
Sellami, Sana ;
Chbeir, Richard ;
Bungartz, Hans-Joachim .
BIG DATA ANALYTICS AND KNOWLEDGE DISCOVERY, DAWAK 2024, 2024, 14912 :231-238
[44]   Insightful Simplicity: Dissimilarity in Time Series Anomaly Detection [J].
Zhong, Zhijie ;
Yu, Zhiwen ;
Chen, Jiahui ;
Yang, Kaixiang .
PROCEEDINGS OF THE ACM TURING AWARD CELEBRATION CONFERENCE-CHINA 2024, ACM-TURC 2024, 2024, :242-243
[45]   Local Evaluation of Time Series Anomaly Detection Algorithms [J].
Huet, Alexis ;
Navarro, Jose Manuel ;
Rossi, Dario .
PROCEEDINGS OF THE 28TH ACM SIGKDD CONFERENCE ON KNOWLEDGE DISCOVERY AND DATA MINING, KDD 2022, 2022, :635-645
[46]   A new distributional treatment for time series anomaly detection [J].
Kai Ming Ting ;
Zongyou Liu ;
Lei Gong ;
Hang Zhang ;
Ye Zhu .
The VLDB Journal, 2024, 33 :753-780
[47]   A Novel Hybrid Methodology for Anomaly Detection in Time Series [J].
Begic Fazlic, Lejla ;
Halawa, Ahmed ;
Schmeink, Anke ;
Lipp, Robert ;
Martin, Lukas ;
Peine, Arne ;
Morgen, Marlies ;
Vollmer, Thomas ;
Winter, Stefan ;
Dartmann, Guido .
INTERNATIONAL JOURNAL OF COMPUTATIONAL INTELLIGENCE SYSTEMS, 2022, 15 (01)
[48]   Deep Learning for Time Series Anomaly Detection: A Survey [J].
Darban, Zahra zamanzadeh ;
Webb, Geoffrey i. ;
Pan, Shirui ;
Aggarwal, Charu ;
Salehi, Mahsa .
ACM COMPUTING SURVEYS, 2025, 57 (01)
[49]   Anomaly detection in time series based on interval sets [J].
Ren, Huorong ;
Liu, Mingming ;
Liao, Xiujuan ;
Liang, Li ;
Ye, Zhixing ;
Li, Zhiwu .
IEEJ TRANSACTIONS ON ELECTRICAL AND ELECTRONIC ENGINEERING, 2018, 13 (05) :757-762
[50]   A Dilated Transformer Network for Time Series Anomaly Detection [J].
Wu, Bo ;
Yao, Zhenjie ;
Tu, Yanhui ;
Chen, Yixin .
2022 IEEE 34TH INTERNATIONAL CONFERENCE ON TOOLS WITH ARTIFICIAL INTELLIGENCE, ICTAI, 2022, :48-52