面向工业传感网络的时间序列异常检测综述

doi:10.11959/j.issn.2096-109x.2024050

摘要/Abstract

摘要：

随着工业控制系统与信息网络的深度融合，工业关键基础设备的网络化、智能化成为未来工业发展的趋势。工业传感网络作为工业系统网络化的重要组成部分，其数据安全已成为被工业安全领域广泛关注。工业传感网络数据异常影响工业控制系统的物理安全、信息安全和网络安全。工业传感网络异常检测是面向网络攻击及物理故障，通过对复杂、多层次、多尺度的传感时间序列分析，发现隐蔽的异常逻辑及故障原因的方法。总结了工业传感网络异常的成因，系统地综述了工业传感网络异常检测的研究进展，从时序特征、时空多尺度及非结构图表征3个视角，对工业传感网络异常检测的关键技术及典型方法进行分类阐述，分析现有各类方法的发展脉络及主要突破。介绍了用于工业传感网络的数据集和评价指标，及方法的检测效果，并通过对比这些方法的实验结果，说明了各方法的特点及技术侧重，给出了现有工作的应用前景，梳理出当前异常检测方法在实际应用中所面临的挑战。最后提出了工业传感网络异常检测发展趋势及未来的研究方向。

关键词: 工业控制系统, 传感网络, 时间序列, 异常检测

Abstract:

The deep integration of industrial control systems and information networks drives the trend towards networking and intelligence in future industrial development. Industrial sensor networks, crucial for industrial system networking, raise concerns in industrial security, particularly regarding data security. Anomalies in industrial sensor network data impact the physical, information, and network security of industrial control systems. Industrial sensor network anomaly detection, addressing network attacks and physical faults, involves analyzing complex, multi-layered, and multi-scale sensor time series data to discover hidden anomalous logic and fault causes. The causes of anomalies in industrial sensor networks were summarized, research progress in industrial sensor network anomaly detection was reviewed systematically, and key technologies and typical methods were explained categorically from three perspectives: time series features, spatiotemporal multiscale, and non-structured graph representation. The developmental trajectories and major breakthroughs of various existing methods were analyzed and consolidated. Datasets and evaluation metrics currently used for industrial sensor networks were introduced, the detection performance of existing methods was summarized, and through comparative analysis of experimental results, the characteristics and technical focuses of each method were highlighted. The application prospects of existing work were pointed out and the challenges faced by current anomaly detection methods in practical applications were outlined. Future development trends and research directions for industrial sensor network anomaly detection were suggested.

Key words: industrial control system, sensor network, time series, anomaly detection

中图分类号:

TP309

吴越, 曹国彦. 面向工业传感网络的时间序列异常检测综述[J]. 网络与信息安全学报, 2024, 10(4): 17-36.

Yue WU, Guoyan CAO. Survey of time series anomaly detection for industrial sensor networks[J]. Chinese Journal of Network and Information Security, 2024, 10(4): 17-36.

图/表 7

图1

表1

图2

图3

表2

表3

表4

参考文献 134

1	FALLIERE N, MURCHU L O, CHIEN E. W32. stuxnet dossier[J]. White Paper, 2011, 5(6): 29.
2	BACKMAN K. When intrusions don’t align: a new water watering hole and oldsmar[EB].
3	LAKSHMANAN R. Cyber attack in iran reportedly cripples gas stations across the country[EB].
4	杨婷, 张嘉元, 黄在起, 等. 工业控制系统安全综述[J]. 计算机研究与发展, 2022, 59(5): 1035-1053.
	YANG T, ZHANG J Y, HUANG Z Q, et al. Survey of industrial control system security[J]. Journal of Computer Research and Development, 2022, 59(5): 1035-1053.
5	CHOI K, YI J, PARK C, et al. Deep learning for anomaly detection in time-series data: review, analysis, and guidelines[J]. IEEE Access, 2021: 120043-120065.
6	SHYU M L, CHEN S C, SARINNAPAKOR K, et al. A novel anomaly detection scheme based on principal component classifier[C]//Proceedings of IEEE Foundations and New Directions of Data Mining Workshop. IEEE Press, 2003: 172-179.
7	ANGIULLI F, PIZZUTI C. Fast outlier detection in high dimensional spaces[C]//Proceedings of European Conference on Principles of Data Mining and Knowledge Discovery. Berlin, Heidelberg: Springer Berlin Heidelberg, 2002: 15-27.
8	BREUNIG M M, KRIEGEL H P, NG R T, et al. Lof: identifying density-based local outliers[C]//Proceedings of 2000 ACM SIGMOD International Conference on Management of Data. 2000: 93-104.
9	SCHLKOPF B, PLATT J C, SHAWE-TAYLOR J, et al. Estimating the support of a high-dimensional distribution[J]. Neural Computation, 2001, 13(7): 1443-1471.
10	CONTRERAS J, ESPINOLA E, NOGALES F J, et al. ARIMA models to predict next-day electricity prices[J]. IEEE Transactions on Power Systems, 2003, 18(3): 1014-1020.
11	KIM D, YANG H, CHUNG M, ET AL. Squeezed convolutional variational autoencoder for unsupervised anomaly detection in edge device industrial internet of things[C]//Proceedings of 2018 IEEE International Conference on Information and Computer Technologies (ICICT). IEEE, 2018: 67-71.
12	CHEN T, GUESTRIN C. Xgboost: a scalable tree boosting system[C]//Proceedings of 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining. ACM, 2016: 785-794.
13	ZAREMBA W, SUTSKEVER I, VINYALS O. Recurrent neural network regularization[EB]. arXiv Preprint arXiv: , 2014.
14	BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB]. arXiv Preprint arXiv: , 2018.
15	GORI M, MONFARDINI G, SCARSELLI F, et al. A new model for learning in graph domains[C]//Proceedings of 2005 IEEE International Joint Conference on Neural Networks, 2005, 2: 729-734.
16	VASWANI A, SHAZEER N, PARMAR N, et al. Attention is all you need[J]. Advances in Neural Information Processing Systems, 2017: 30.
17	UMER M A, JUNEJO K N, JILANI M T, et al. Machine learning for intrusion detection in industrial control systems: applications, challenges, and recommendations[J]. International Journal of Critical Infrastructure Protection, 2022, 38: 100516.
18	KOAY A M Y, KO R K L, HETTEMA H, et al. Machine learning in industrial control system (ICS) security: current landscape, opportunities and challenges[J]. Journal of Intelligent Information Systems, 2023, 60(2): 377-405.
19	唐士杰, 袁方, 李俊, 等. 工业控制系统关键组件安全风险综述[J]. 网络与信息安全学报, 2022, 8(3): 1-17.
	TANG S J, YUAN F, LI J, et al. Review on security risks of key components in industrial control system[J]. Chinese Journal of Network and Information Security, 2022, 8(3): 1-17.
20	DARBAN Z Z, WEBB G I, PAN S, et al. Deep learning for time series anomaly detection: a survey[EB]. arXiv Preprint arXiv: , 2022.
21	LUO Y, XIAO Y, CHENG L, et al. Deep learning-based anomaly detection in cyber-physical systems: progress and opportunities[J]. ACM Computing Surveys (CSUR), 2021, 54(5): 1-36.
22	孙海丽, 龙翔, 韩兰胜, 等. 工业物联网异常检测技术综述[J]. 通信学报, 2022, 43(3): 196-210.
	SUN H L, LONG X, HAN L S, et al. Overview of anomaly detection techniques for industrial internet of things[J]. Journal on Communications, 2022, 43(3): 196-210.
23	MURALEEDHARAN R, OSADCIW L A. Cross layer denial of service attacks in wireless sensor network using swarm intelligence[C]//Proceedings of IEEE 40th Annual Conference on Information Sciences and Systems. IEEE, 2006: 1653-1658.
24	PENG L, CAO X, SUN C, et al. Energy efficient jamming attack schedule against remote state estimation in wireless cyber physical systems[J]. Neurocomputing, 2018, 272: 571-583.
25	ZHANG H, CHENG P, SHI L, et al. Optimal DoS attack scheduling in wireless networked control system[J]. IEEE Transactions on Control Systems Technology, 2015, 24(3): 843-862.
26	QIN J, LI M, SHI L, et al. Optimal denial-of-service attack scheduling with energy constraint[J]. IEEE Transactions on Automatic Control, 2015, 60(11): 3023-3028.
27	QIN J, LI M, SHI L, et al. Optimal denial-of-service attack scheduling with energy constraint over packet-dropping networks[J]. IEEE Transactions on Automatic Control, 2017, 63(6): 1648-1663.
28	ZHANG J, SUN J, LIN H. Optimal DoS attack schedules on remote state estimation under multi-sensor round-robin protocol[J]. Automatica, 2021, 127: 109517.
29	ZHANG X M, HAN Q L, GE X, et al. Networked control systems: a survey of trends and techniques[J]. IEEE/CAA Journal of Automatica Sinica, 2020, 7(1): 1-17.
30	DUO W, ZHOU M C, ABUSORRAH A. A survey of cyber attacks on cyber physical systems: recent advances and challenges[J]. IEEE/CAA Journal of Automatica Sinica, 2022, 9(5): 784-800.
31	WU G, SUN J, CHEN J. Optimal data injection attacks in cyber-physical systems[J]. IEEE Transactions on Cybernetics, 2018, 48(12): 3302-3312.
32	MOUSAVINEJAD E, YANG F, HAN Q L, et al. A novel cyber attack detection method in networked control systems[J]. IEEE Transactions on Cybernetics, 2018, 48(11): 3254-3264.
33	WU S, GUO Z, SHI D, et al. Optimal innovation-based deception attack on remote state estimation[C]//Proceedings of 2017 American Control Conference (ACC). IEEE, 2017: 3017-3022.
34	ZHANG Q, LIU K, XIA Y, et al. Optimal stealthy deception attack against cyber-physical systems[J]. IEEE Transactions on Cybernetics. 2019, 50(9): 3963-3972.
35	LI B, LU R, CHOO K K R, et al. On reliability analysis of smart grids under topology attacks: a stochastic petri net approach[J]. ACM Transactions on Cyber-Physical Systems, 2018, 3(1): 1-25.
36	MEIRA-GóES R, KANG E, KWONG R H, et al. Synthesis of sensor deception attacks at the supervisory layer of cyber-physical systems[J]. Automatica. 2020, 121: 109172.
37	WANG K, GAO H, XU X, et al. An energy-efficient reliable data transmission scheme for complex environmental monitoring in underwater acoustic sensor networks[J]. IEEE Sensors Journal, 2015, 16(11): 4051-4062.
38	YUAN L, WANG K, MIYAZAKI T, et al. Optimal transmission strategy for sensors to defend against eavesdropping and jamming attacks[C]//Proceedings of 2017 IEEE International Conference on Communications (ICC). IEEE, 2017: 1-6.
39	YIN X, LI Z, WANG W, et al. Infinite-step opacity and k-step opacity of stochastic discrete-event systems[J]. Automatica. 2019, 99: 266-274.
40	AN L, YANG G H. Opacity enforcement for confidential robust control in linear cyber-physical systems[J]. IEEE Transactions on Automatic Control, 2019, 65(3): 1234-1241.
41	YANG S, HOU J, YIN X, et al. Opacity of networked supervisory control systems over insecure communication channels[J]. IEEE Transactions on Control of Network Systems, 2021, 8(2): 884-896.
42	DEB D, CHAKRABORTY S R, LAGINENI M, et al. Security analysis of MITM attack on SCADA network[C]//Proceedings of Machine Learning, Image Processing, Network Security and Data Sciences: Second International Conference, MIND 2020, Silchar: SingaporeSpringer, 2020: 501-512.
43	HUNDMAN K, CONSTANTINOU V, LAPORTE C, et al. Detecting spacecraft anomalies using LSTMs and nonparametric dynamic thresholding[C]//Proceedings of 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2018: 387-395.
44	WU H, GENG Y, LIU K, et al. Research on programmable logic controller security[C]//Proceedings of IOP Conference Series: Materials Science and Engineering. IOP Publishing, 2019, 569(4): 042031.
45	GUGULOTHU N, MALHOTRA P, VIG L, et al. Sparse neural networks for anomaly detection in high-dimensional time series[C]//Proceedings of AI4IOT Workshop in Conjunction with ICML, IJCAI and ECAI. 2018: 1551-3203.
46	ZONG B, SONG Q, MIN M R, et al. Deep autoencoding gaussian mixture model for unsupervised anomaly detection[C]//Proceedings of International Conference on Learning Representations(ICLR). 2018.
47	KIEU T, YANG B, GUO C, et al. Outlier detection for time series with recurrent autoencoder ensembles[C]//Proceedings of International Joint Conference on Artificial Intelligence(IJCAI). 2019: 2725-2732.
48	AUDIBERT J, MICHIARDI P, GUYARD F, et al. USAD: unsupervised anomaly detection on multivariate time series[C]//Proceedings of 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020: 3395-3404.
49	GOODGE A, HOOI B, NG S K, et al. Robustness of autoencoders for anomaly detection under adversarial impact[C]//Proceedings of 29th International Conference on International Joint Conferences on Artificial Intelligence. 2021: 1244-1250.
50	ABDULAAL A, LIU Z, LANCEWICKI T. Practical approach to asynchronous multivariate time series anomaly detection and localization[C]//Proceedings of 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021: 2485-2494.
51	ZHANG Y, WANG J, CHEN Y, et al. Adaptive memory networks with self-supervised learning for unsupervised anomaly detection[J]. IEEE Transactions on Knowledge and Data Engineering, 2023, 35(12): 12068-12080.
52	PARK D, HOSHI Y, KEMP C C. A multimodal anomaly detector for robot-assisted feeding using an LSTM-based variational autoencoder[J]. IEEE Robotics and Automation Letters, 2018, 3(3): 1544-1551.
53	GUO Y, LIAO W, WANG Q, et al. Multidimensional time series anomaly detection: a GRU-based gaussian mixture variational autoencoder approach[C]//Proceedings of Asian Conference on Machine Learning. PMLR, 2018: 97-112.
54	SU Y, ZHAO Y, NIU C, et al. Robust anomaly detection for multivariate time series through stochastic recurrent neural network[C]//Proceedings of 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2019: 2828-2837.
55	LI L, YAN J, WANG H, et al. Anomaly detection of time series with smoothness-inducing sequential variational autoencoder[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 32(3): 1177-1191.
56	NIU Z, YU K, WU X. LSTM-based VAE-GAN for time-series anomaly detection[J]. Sensors. 2020, 20(13): 3738.
57	ZHANG C, LI S, ZHANG H, et al. VELC: A new variational autoencoder based model for time series anomaly detection[J]. arXiv Preprint arXiv: , 2019.
58	CHEN R Q, SHI G H, ZHAO W L, et al. A joint model for it operation series prediction and anomaly detection[J]. Neurocomputing, 2021, 448(8): 130-139.
59	LI L, YAN J, WEN Q, et al. Learning robust deep state space for unsupervised anomaly detection in contaminated time-series[J]. IEEE Transactions on Knowledge and Data Engineering. 2022, 35(6): 6058-6072.
60	HOCHREITER S, SCHMIDHUBER J. Long short-term memory[J]. Neural Computation, 1997, 9(8): 1735-1780.
61	CHO K, VAN MERRIENBOER B, GULCEHRE C, et al. Learning phrase representations using RNN encoder-decoder for statistical machine translation[EB]. arXiv Preprint arXiv: , 2014.
62	LE Q V, JAITLY N, HINTON G E. A simple way to initialize recurrent networks of rectified linear units[EB]. arXiv Preprint arXiv:, 2015.
63	JING L, GüLEHRE A, PEURIFOY J, et al. Gated orthogonal recurrent units: on learning to forget[J]. Neural Computation, 2019, 31(4): 765-783.
64	CHEN L, CHEN D, YANG F, et al. A deep multi-task representation learning method for time series classification and retrieval[J]. Information Sciences, 2021, 555: 17-32.
65	GOH J, ADEPU S, TAN M, et al. Anomaly detection in cyber physical systems using recurrent neural networks[C]//Proceedings of 2017 IEEE 18th International Symposium on High Assurance Systems Engineering (HASE). IEEE, 2017: 140-145.
66	DING N, MA H X, GAO H, et al. Real-time anomaly detection based on long short-term memory and gaussian mixture model[J]. Computers & Electrical Engineering. 2019, 79: 106458.
67	SHEN L, LI Z, KWOK J. Timeseries anomaly detection using temporal hierarchical one-class network[J]. Advances in Neural Information Processing Systems, 2020, 33: 13016-13026.
68	WU W, HE L, LIN W, et al. Developing an unsupervised real-time anomaly detection scheme for time series with multi-seasonality[J]. IEEE Transactions on Knowledge and Data Engineering, 2020, 34(9): 4147-4160.
69	VOS K, PENG Z, JENKINS C, et al. Vibration-based anomaly detection using LSTM/SVM approaches[J]. Mechanical Systems and Signal Processing, 2022, 169: 108752.
70	MUNIR M, SIDDIQUI S A, DENGEL A, et al. DeepAnt: a deep learning approach for unsupervised anomaly detection in time series[J]. IEEE Access, 2018, 7: 1991-2005.
71	YIN C, ZHANG S, WANG J, et al. Anomaly detection based on convolutional recurrent autoencoder for IoT time series[J]. IEEE Transactions on Systems, Man, and Cybernetics: Systems, 2020, 52(1): 112-122.
72	LIU F, ZHOU X, CAO J, et al. Anomaly detection in quasi-periodic time series based on automatic data segmentation and attentional LSTM-CNN[J]. IEEE Transactions on Knowledge & Data Engineering, 2022, 34(06): 2626-2640.
73	BAI S, KOLTER J Z, KOLTUN V. An empirical evaluation of generic convolutional and recurrent networks for sequence modeling[EB]. arXiv Preprint arXiv: , 2018.
74	CHENG Y, XU Y, ZHONG H, et al. HS-TCN: a semi-supervised hierarchical stacking temporal convolutional network for anomaly detection in IoT[C]//Proceedings of 2019 IEEE 38th International Performance Computing and Communications Conference (IPCCC). IEEE, 2019: 1-7.
75	LIU J, ZHU H, LIU Y, et al. Anomaly detection for time series using temporal convolutional networks and Gaussian mixture model[C]//Proceedings of Journal of Physics: Conference Series. IOP Publishing, 2019, 1187(4): 042111.
76	HE Y, ZHAO J. Temporal convolutional networks for anomaly detection in time series[C]//Proceedings of Journal of Physics: Conference Series. IOP Publishing, 2019, 1213(4): 042050.
77	ZHOU B, LIU S, HOOI B, et al. BeatGAN: anomalous rhythm detection using adversarially generated time series[C]//Proceedings of International Joint Conference on Artificial Intelligence (IJCAI). 2019: 4433-4439.
78	CHOI Y, LIM H, CHOI H, et al. GAN-based anomaly detection and localization of multivariate time series data for power plant[C]//Proceedings of 2020 IEEE International Conference on Big Data And Smart Computing (BigComp). IEEE, 2020: 71-74.
79	CHEN X, DENG L, HUANG F, et al. Daemon: unsupervised anomaly detection and interpretation for multivariate time series[C]//Proceedings of 2021 IEEE 37th International Conference on Data Engineering (ICDE). IEEE, 2021: 2225-2230.
80	DU B, SUN X, YE J, et al. GAN-based anomaly detection for multivariate time series using polluted training set[J]. IEEE Transactions on Knowledge and Data Engineering. 2021. 35(12): 12208-12219.
81	LI Y, PENG X, ZHANG J, et al. DCT-GAN: Dilated convolutional transformer-based GAN for time series anomaly detection[J]. IEEE Transactions on Knowledge and Data Engineering. 2023, 35(4): 3632-3644.
82	胡智超, 余翔湛, 刘立坤, 等. 基于上下文生成对抗网络的时间序列异常检测方法[J]. 哈尔滨工业大学学报. 2024, 56(5): 1-11.
	HU Z C, YU X Z, LIU L K, et al. Time series anomaly detection with contextual generative adversarial network[J]. Journal of Harbin Institute of Technology. 2024, 56(5): 1-11.
83	SONG H, RAJAN D, THIAGARAJAN J J, et al. Attend and diagnose: clinical time series analysis using attention models[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2018. 32(1).
84	MENG H, ZHANG Y, LI Y, et al. Spacecraft anomaly detection via transformer reconstruction error[C]//Proceedings of International Conference on Aerospace System Science and Engineering 2019. Springer Singapore, 2020: 351-362.
85	XU J, WU H, WANG J, et al. Anomaly transformer: time series anomaly detection with association discrepancy[J]. arXiv Preprint arXiv: , 2021.
86	TULI S, CASALE G, JENNINGS N R. TranAD: deep transformer networks for anomaly detection in multivariate time series data[J]. arXiv Preprint arXiv: , 2022.
87	KIM J, KANG H, KANG P. Time-series anomaly detection with stacked transformer representations and 1d convolutional network[J]. Engineering Applications of Artificial Intelligence. 2023, 120: 105964.
88	霍纬纲, 梁锐, 李永华. 基于随机Transformer的多维时间序列异常检测模型[J]. 通信学报, 2023, 44(2): 94-103.
	HUO W G, LIANG R, LI Y H. Anomaly detection model for multivariate time series based on stochastic transformer[J]. Journal on Communications, 2023, 44(2): 94-103.
89	ZHANG C, SONG D, CHEN Y, et al. A deep neural network for unsupervised anomaly detection and diagnosis in multivariate time series data[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2019. 33(1): 1409-1416.
90	HE Z, CHEN P, LI X, et al. A spatiotemporal deep learning approach for unsupervised anomaly detection in cloud systems[J]. IEEE Transactions on Neural Networks and Learning Systems, 2020, 34(4): 1705-1719.
91	LI Z, ZHAO Y, HAN J, et al. Multivariate time series anomaly detection and interpretation using hierarchical inter-metric and temporal embedding[C]//Proceedings of 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining. 2021: 3220-3230.
92	LI D, CHEN D, JIN B, et al. MAD-GAN: Multivariate anomaly detection for time series data with generative adversarial networks[C]//Proceedings of International Conference on Artificial Neural Networks. Springer, Cham, 2019: 703-716.
93	WANG X, PI D, ZHANG X, et al. Variational transformer-based anomaly detection approach for multivariate time series[J]. Measurement, 2022, 191: 110791.
94	梁李芳, 关东海, 张吉, 等. 基于时空注意力机制的多元时间序列异常检测[J]. 计算机科学, 2023, 50(S2): 450-457.
	LIANG L F, GUAN D H, ZHANG J, et al. Spatial-temporal attention mechanism based anomaly detection for multivariate times series[J]. Computer Science, 2023, 50(S2): 450-457.
95	张国华, 燕雪峰, 关东海. 基于多模态特征融合的时间序列异常检测[J]. 计算机科学, 2023, 50(S1): 548-554.
	ZHANG G H, YAN X F, GUAN D H. Anomaly detection of time-series based on multi-modal feature fusion[J]. Computer Science, 2023, 50(S1): 548-554.
96	WU H, HU T, LIU Y, et al. TimesNet: temporal 2d-variation modeling for general time series analysis[C]//Proceedings of the Eleventh International Conference on Learning Representations (ICLR). 2023.
97	KIPF T N, WELLING M. Semi-supervised classification with graph convolutional networks[EB]. arXiv Preprint arXiv: , 2016.
98	VELIKOVI P, CUCURULL G, CASANOVA A. Graph attention networks[C]//Proceedings of International Conference on Learning Represent- ations(ICLR). 2018.
99	ZHU Y, XU W, ZHANG J, et al. A survey on graph structure learning: progress and opportunities[J]. arXiv Preprint arXiv: , 2021.
100	LI R, WANG S, ZHU F, et al. Adaptive graph convolutional neural networks[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2018, 32(1): 3546-3553.
101	ZHAO T, LIU Y, NEVES L, et al. Data augmentation for graph neural networks[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2021, 35(12): 11015- 11023.
102	CHEN Y, WU L, ZAKI M. Iterative deep graph learning for graph neural networks: Better and robust node embeddings[J]. Advances in Neural Information Processing Systems, 2020, 33: 19314-19326.
103	JIANG B, ZHANG Z, LIN D, et al. Semi-supervised learning with graph learning-convolutional networks[C]//Proceedings of IEEE/CVF Conference on Computer Vision and Pattern Recognition. 2019: 11313-11320.
104	LUO D, CHENG W, YU W, et al. Learning to drop: robust graph neural network via topological denoising[C]//Proceedings of 14th ACM International Conference on Web Search and Data Mining. 2021: 779-787.
105	SUN Q, LI J, PENG H, et al. Graph structure learning with variational information bottleneck[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2022, 36(4): 4165- 4174.
106	JIN W, MA Y, LIU X, et al. Graph structure learning for robust graph neural networks[C]//Proceedings of 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining. 2020: 66-74.
107	XU H, XIANG L, YU J, et al. Speedup robust graph structure learning with low-rank information[C]//Proceedings of 30th ACM International Conference on Information & Knowledge Management. 2021: 2241-2250.
108	LIU Y, ZHENG Y, ZHANG D, et al. Towards unsupervised deep graph structure learning[C]//Proceedings of ACM Web Conference 2022. 2022: 1392-1403.
109	ZHAO H, WANG Y, DUAN J, et al. Multivariate time-series anomaly detection via graph attention network[C]//Proceedings of IEEE International Conference on Data Mining (ICDM). IEEE, 2020: 841-850.
110	DENG A, HOOI B. Graph neural network-based anomaly detection in multivariate time series[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2021. 35(5): 4027- 4035.
111	CHEN Z, CHEN D, ZHANG X, et al. Learning graph structures with transformer for multivariate timeseries anomaly detection in iot[J]. IEEE Internet of Things Journal, 2021, 9(12): 9179-9189.
112	DAI E, CHEN J. Graph-augmented normalizing flows for anomaly detection of multiple time series[EB]. arXiv Preprint arXiv: , 2022.
113	DING C, SUN S, ZHAO J. MST-GAN: a multimodal spatial- temporal graph attention network for time series anomaly detection[J]. Information Fusion. 2023, 89: 527-536.
114	GOH J, ADEPU S, JUNEJO K N, et al. A dataset to support research in the design of secure water treatment systems[C]//Proceedings of Critical Information Infrastructures Security: 11th International Conference, CRITIS 2016, Paris: Springer International Publishing, 2017: 88-99.
115	ADEPU S, MATHUR A. An investigation into the response of a water treatment system to cyber attacks[C]//Proceedings of 2016 IEEE 17th International Symposium on High Assurance Systems Engineering (HASE). IEEE, 2016: 141-148.
116	AHMED C M, PALLETI V R, MATHUR A P. WADI: a water distribution testbed for research in the design of secure cyber physical systems[C]//Proceedings of 3rd International Workshop on Cyber- physical Systems for Smart Water Networks. 2017: 25-28.
117	ADEPU S, MATHUR A. Generalized attacker and attack models for cyber physical systems[C]//Proceedings of 2016 IEEE 40th Annual Computer Software and Applications Conference (COMPSAC). IEEE, 2016, 1: 283-292.
118	JUBA B, LE H S. Precision-recall versus accuracy and the role of large data sets[C]//Proceedings of AAAI Conference on Artificial Intelligence. 2019, 33(1): 4039-4048.
119	冯兆文, 吴越, 周奇, 等. 面向工业流程的多级图卷积异常检测与定位方法[C]//2022中国自动化大会，2022.
	FENG Z W, WU Y, ZHOU Q, et al. A multi-graph convolution anomaly detection and localization method for industrial process[C]//Proceedings of 2022 The China Automation Congress, 2022.
120	RAS E, WILD F, STAHL C, et al. Bridging the skills gap of workers in Industry 4.0 by human performance augmentation tools: challenges and roadmap[C]//Proceedings of the 10th International Conference on PErvasive Technologies Related to Assistive Environments. 2017: 428-432.
121	AHMED C M, MR G R, MATHUR A P. Challenges in machine learning based approaches for real-time anomaly detection in industrial control systems[C]//Proceedings of 6th ACM on Cyber-physical System Security Workshop. 2020: 23-29.
122	ISMAIL A A, GUNADY M, CORRADA B H, et al. Benchmarking deep learning interpretability in time series predictions[J]. Advances in Neural Information Processing Systems, 2020, 33: 6441-6452.
123	ZHANF X, WANG N, SHEN H, et al. Interpretable deep learning under fire[C]//Proceedings of 29th {USENIX} Security Symposium ({USENIX} Security 20). 2020.
124	RAISSI M, PERDIKARIS P, KARNIADAKIS G E. Physics informed deep learning (part I): data-driven solutions of nonlinear partial differential equations[EB]. arXiv Preprint arXiv: , 2017.
125	RAISSI M, PERDIKARIS P, KARNIADAKIS G E. Physics informed deep learning (part II): data-driven discovery of nonlinear partial differential equations[EB]. arXiv Preprint arXiv: 1711.10566. 2017.
126	ABREU E, FLORINDO J B. A study on a feedforward neural network to solve partial differential equations in hyperbolic-transport problems[C]//Proceedings of Computational Science-ICCS 2021: 21st International Conference, Krakow, Poland, June 16-18, 2021, Proceedings, Part II 21. Springer International Publishing, 2021: 398-411.
127	KOVACS A, EXL L, KORNDLL A, et al. Conditional physics informed neural networks[J]. Communications in Nonlinear Science and Numerical Simulation, 2022, 104: 106041.
128	YUCESAN Y A, VIANA F A C. Hybrid physics-informed neural networks for main bearing fatigue prognosis with visual grease inspection[J]. Computers in Industry, 2021, 125: 103386.
129	VIANA F A C, NASCIMENTO R G, DOURADO A, et al. Estimating model inadequacy in ordinary differential equations with physics informed neural networks[J]. Computers & Structures, 2021, 245: 106458.
130	JIW, CHANG J, XU H X, et al. Recent advances in metasurface design and quantum optics applications with machine learning, physics-informed neural networks, and topology optimization methods[J]. Light: Science & Applications, 2023, 12(1): 169.
131	ROY A M, BOSE R, SUNDARARAGHAVAN V, et al. Deep learningaccelerated computational framework based on physics informed neural network for the solution of linear elasticity[J]. Neural Networks, 2023, 162: 472-489.
132	MISHRA S, MOLINARO R. Estimates on the generalization error of physics-informed neural networks for approximating a class of inverse problems for PDEs[J]. IMA Journal of Numerical Analysis, 2022, 42(2): 981-1022.
133	MOSELEY B, MARKHAM A, NISSEN-MEYER T. Finite basis physics-informed neural networks (FBPINNs): a scalable domain decomposition approach for solving differential equations[J]. Advances in Computational Mathematics, 2023, 49(4): 62.
134	WU C, ZHU M, TAN Q, et al. A comprehensive study of non-adaptive and residual-based adaptive sampling for physics-informed neural networks[J]. Computer Methods in Applied Mechanics and Engineering, 2023, 403: 115671.

相关工作	异常类型	应用领域	简要描述	涉及安全属性
相关工作	异常类型	应用领域	简要描述	可用性	完整性	机密性
Muraleedharan et al^［23］	DoS	智能读卡系统	传感器通过蠕虫洞进行伪装	●	○	○
Peng et al^［24］	DoS	网络物理系统	干扰传感器和远程间的通信	●	○	○
Zhang et al^［25］	DoS	无线网络系统	最大化二次高斯代价函数	●	○	○
Qin et al^{［26， 27］}	DoS	网络物理系统	研究未攻击下的数据丢包	●	○	○
Zhang et al^［28］	DoS	网络物理系统	多传感器共享公共通信信道	●	○	○
Wu et al^［31］	FDI	网络物理系统	使用时变权重矩阵增加难度	○	●	○
Mousavinejad et al^［32］	FDI	网络化控制系统	用传感器测量数据更新预测	○	●	○
Wu et al^［33］	FDI	网络物理系统	在智能动态传感中降低质量	○	●	○
Zhang et al^［34］	FDI	无人地面飞行器	用Kullback-Leibler约束	○	●	○
Li et al^［35］	FDI	智能电网	保守和侵略两种拓扑攻击	○	●	○
Wang et al^［37］	被动	水声传感网络	建立能量和位置的消耗模型	○	○	●
Yuan et al^［38］	被动	网络物理系统	待反馈随机算法最大化传输	○	○	●

方法	精确率
方法	SWaT	WADI	SMAP	MSL	SMD
DAGMM	27.46%	87.79%	58.45%	54.12%	91.03%
LSTM-VAE	96.24%	87.79%	85.51%	52.57%	—
USAD	99.77%	18.73%	74.80%	79.49%	90.60%
OmniAnomaly	97.82%	31.58%	81.30%	78.48%	88.81%
LSTM-NDT	77.78%	1.38	85.23%	62.88%	97.36%
Anomaly Transformer	72.51%	—	91.85%	79.61%	88.91%
TranAD	97.60%	35.29%	80.43%	90.38%	92.62%
MSCRED	99.92%	25.13%	81.75%	89.12%	72.76%
MAD-GAN	98.97%	41.44%	80.49%	85.17%	99.91%
TimesNet	88.31%	—	92.52%	83.92%	88.66%
MTAD-GAT	97.18%	28.18%	89.06%	87.54%	82.10%
GDN	99.35%	97.50%	74.80%	93.08%	71.70%
GTA	88.10%	83.61%	91.76%	91.17%	—

方法	召回率
方法	SWaT	WADI	SMAP	MSL	SMD
DAGMM	69.52%	26.99%	90.58%	99.34%	99.14%
LSTM-VAE	59.91%	14.45%	63.66%	95.46%	—
USAD	68.79%	82.96%	96.27%	99.12%	99.74%
OmniAnomaly	69.57%	65.41%	94.19%	99.24%	99.85%
LSTM-NDT	51.09%	78.23%	73.26%	100.0%	84.40%
Anomaly Transformer	97.32%	—	58.11%	87.37%	82.23%
TranAD	69.97%	82.96%	99.99%	99.99%	99.74%
MSCRED	67.70%	73.19%	92.16%	98.62%	99.74%
MAD-GAN	63.74%	33.92%	82.14%	89.91%	84.40%
TimesNet	96.24%	—	58.29%	86.42%	83.14%
MTAD-GAT	69.57%	80.12%	91.23%	94.40%	92.15%
GDN	68.12%	40.19%	98.91%	98.92%	99.74%
GTA	88.10%	83.61%	91.76%	91.17%	—

方法	F1分数
方法	SWaT	WADI	SMAP	MSL	SMD
DAGMM	0.39	0.36	0.71	0.67	0.95
LSTM-VAE	0.74	0.25	0.73	0.68	0.83
USAD	0.81	0.31	0.84	0.88	0.95
OmniAnomaly	0.82	0.42	0.87	0.88	0.95
LSTM-NDT	0.62	0.03	0.79	0.77	0.90
Anomaly Transformer	0.83	—	0.71	0.83	0.85
TranAD	0.82	0.50	0.89	0.95	0.96
MSCRED	0.81	0.37	0.87	0.94	0.84
MAD-GAN	0.77	0.37	0.81	0.87	0.91
TimesNet	0.92	—	0.72	0.85	0.86
MTAD-GAT	0.81	0.42	0.90	0.91	0.87
GDN	0.81	0.57	0.85	0.96	0.83
GTA	0.91	0.84	0.90	0.91	—

[1]	曹艺怀, 陈伟, 张帆, 吴礼发. 面向高速网络流量的加密混淆型WebShell检测[J]. 网络与信息安全学报, 2022, 8(4): 119-130.
[2]	石灏苒, 吉立新, 刘树新, 王庚润. 基于半局部结构的异常连边识别算法[J]. 网络与信息安全学报, 2022, 8(1): 63-72.
[3]	赵普, 赵文涛, 付章杰, 刘强. 基于Renyi熵的SDN自主防护系统[J]. 网络与信息安全学报, 2021, 7(3): 85-94.
[4]	张颖君,刘尚奇,杨牧,张海霞,黄克振. 基于日志的异常检测技术综述[J]. 网络与信息安全学报, 2020, 6(6): 1-12.
[5]	赵淦森,谢智健,王欣明,何嘉浩,张成志,林成创,ZihengZhou,陈冰川,ChunmingRong. ContractGuard：面向以太坊区块链智能合约的入侵检测系统[J]. 网络与信息安全学报, 2020, 6(2): 35-55.
[6]	黄伟,刘存才,祁思博. 针对设备端口链路的LSTM网络流量预测与链路拥塞方案[J]. 网络与信息安全学报, 2019, 5(6): 50-57.
[7]	王易东, 刘培顺, 王彬. 基于深度学习的系统日志异常检测研究[J]. 网络与信息安全学报, 2019, 5(5): 105-118.
[8]	樊迪,刘静,庄俊玺,赖英旭. 基于因果知识发现的攻击场景重构研究[J]. 网络与信息安全学报, 2017, 3(4): 58-68.
[9]	苗笛,黄斌,李杰. 基于智慧协同网络的传感网络安全备份方法[J]. 网络与信息安全学报, 2017, 3(3): 28-33.
[10]	徐军. 基于生物特性可信接入协议的可信计算移动终端的应用研究[J]. 网络与信息安全学报, 2017, 3(2): 66-76.
[11]	张辉,刘成. 基于改进的SVM方法的异常检测研究[J]. 网络与信息安全学报, 2016, 2(8): 68-73.
[12]	李洪成,吴晓平,姜洪海. 基于改进聚类分析的网络流量异常检测方法[J]. 网络与信息安全学报, 2015, 1(1): 66-71.