USAD: UnSupervised Anomaly Detection on Multivariate Time Series
Open accessThe DOI matches its Crossref record; 19 of the 20 references it cites were found in a registry or an index.
Abstract
The automatic supervision of IT systems is a current challenge at Orange. Given the size and complexity reached by its IT operations, the number of sensors needed to obtain measurements over time, used to infer normal and abnormal behaviors, has increased dramatically making traditional expert-based supervision methods slow or prone to errors. In this paper, we propose a fast and stable method called UnSupervised Anomaly Detection for multivariate time series (USAD) based on adversely trained autoencoders. Its autoencoder architecture makes it capable of learning in an unsupervised way. The use of adversarial training and its architecture allows it to isolate anomalies while providing fast training. We study the properties of our methods through experiments on five public datasets, thus demonstrating its robustness, training speed and high anomaly detection performance. Through a feasibility study using Orange's proprietary data we have been able to validate Orange's requirements on scalability, stability, robustness, training speed and high performance.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“It is beneficial to introduce an adversarial-based SSL, which can further amplify the difference between normal and anomalous data, such as USAD [66] and DAEMON [184].”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [66]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“The core idea behind USAD is to amplify the reconstruction error by adversarial training between two BAEs.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [66]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“USAD [66] is a time series anomaly detection framework that includes two BAE models, and two BAE are defined as AE 1 and AE 2 , respectively.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [66]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Adversarial-based regularization constraints can amplify the score difference between anomalies and normal points, thereby enhancing the accuracy of anomalies identification from another perspective, such as Minmax learning [66], [163] and adversarial learning [184].”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [66]
Experimental — accuracy not yet measuredThe cited source says what the claim attributes to it.
In the citing paper
“RANSynCoders [63], USAD[66], AnomalyTrans [163], and DAEMON [184] employ autoencoder-based reconstruction SSL framework.”
From Self-Supervised Learning for Time Series Analysis: Taxonomy, Progress, and Prospects (2024) · cites this paper as [66]
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“poral data, methods based on recurrent neural networks [7] (RNNs) are very popular.”
MethodGAN(Generative Adversarial Nets)
(2017) · Journal of Japan Society for Fuzzy Theory and Intelligent Informatics · doi:10.3156/jsoft.29.5_177_2 · Cited by 19,270
Learning Internal Representations by Error Propagation
Rumelhart, D. E., Hinton, G. E., & Williams, R. J. (1985) · doi:10.21236/ada164453 · Cited by 16,172
Liu, F. T., Ting, K. M., & Zhou, Z.-H. (2008) · 2008 Eighth IEEE International Conference on Data Mining · doi:10.1109/icdm.2008.17 · Cited by 6,601 · cited 1×
“Figure 2(C) presents the results for m ∈ [ 5 , 10 , 20 , 40 , 100 ] . dimension for Z causes a large loss of information at the encoding .”
Background5th International Conference on Learning Representations (ICLR 17)
Havrylov, S., & Titov, I. (2017) · Cited by 3,503
Robust Anomaly Detection for Multivariate Time Series through Stochastic Recurrent Neural Network
Su, Y., Zhao, Y., Niu, C., Liu, R., Sun, W., & Pei, D. (2019) · Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3292500.3330672 · Cited by 1,804 · cited 9×
“On top, the results obtained with SWaT and WADI datasets are presented, whereas the bottom part of the table reports obtained results from the benchmark proposed by [17], using three remaining datasets.”
BackgroundMethodResultInfluentialDetecting Spacecraft Anomalies Using LSTMs and Nonparametric Dynamic Thresholding
Hundman, K., Constantinou, V., Laporte, C., Colwell, I., & Soderstrom, T. (2018) · Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining · doi:10.1145/3219819.3219845 · Cited by 1,771
Schwartz, R., Dodge, J., Smith, N. A., & Etzioni, O. (2020) · Communications of the ACM · doi:10.1145/3381831 · Cited by 1,647
Deep Learning for Anomaly Detection: A Survey
Chalapathy, R., & Chawla, S. (2019) · arXiv · doi:10.48550/arxiv.1901.03407 · Cited by 1,240 · cited 1×
“Detecting unexpected behavior on a set of measurements correlated with each other over time is an active research discipline called anomaly detection in multivariate time series [2].”
BackgroundA Multimodal Anomaly Detector for Robot-Assisted Feeding Using an LSTM-Based Variational Autoencoder
Park, D., Hoshi, Y., & Kemp, C. C. (2018) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2018.2801475 · Cited by 1,115
Research works printed but not linked: 3
- Ian J. Goodfellow , Jean Pouget-Abadie , Mehdi Mirza , Bing Xu , David Warde-Farley , Sherjil Ozair , Aaron C. Courville , and Yoshua Bengio . 2014 . Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014. Montreal, Quebec, Canada, 2672--2680. Ian J. Goodfellow, Jean Pouget-Abadie, Mehdi Mirza, Bing Xu, David Warde-Farley, Sherjil Ozair, Aaron C. Courville, and Yoshua Bengio. 2014. Generative Adversarial Nets. In Advances in Neural Information Processing Systems 27: Annual Conference on Neural Information Processing Systems 2014. Montreal, Quebec, Canada, 2672--2680.
- Chuxu Zhang , Dongjin Song , Yuncong Chen , Xinyang Feng , Cristian Lumezanu , Wei Cheng , Jingchao Ni , Bo Zong , Haifeng Chen , and Nitesh V. Chawla . 2019. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data . Proceedings of the AAAI Conference on Artificial Intelligence , Vol. 33 ( 2019 ), 1409--1416. Chuxu Zhang, Dongjin Song, Yuncong Chen, Xinyang Feng, Cristian Lumezanu, Wei Cheng, Jingchao Ni, Bo Zong, Haifeng Chen, and Nitesh V. Chawla. 2019. A Deep Neural Network for Unsupervised Anomaly Detection and Diagnosis in Multivariate Time Series Data. Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 33 (2019), 1409--1416.
- Bo Zong , Qi Song , Martin Renqiang Min , Wei Cheng , Cristian Lumezanu , Daeki Cho , and Haifeng Chen . 2018 . Deep autoencoding Gaussian mixture model for unsupervised anomaly detection . In 6th International Conference on Learning Representations, ICLR 2018. Toulon, France, 1--19. Bo Zong, Qi Song, Martin Renqiang Min, Wei Cheng, Cristian Lumezanu, Daeki Cho, and Haifeng Chen. 2018. Deep autoencoding Gaussian mixture model for unsupervised anomaly detection. In 6th International Conference on Learning Representations, ICLR 2018. Toulon, France, 1--19.
Cited by
Items 701–800 of 1,000
RAID: Root Cause Anomaly Identification and Diagnosis
Ky, J. R., Mathieu, B., Lahmadi, A., Wang, M., Marrot, N., & Boutaba, R. (2025) · Lecture notes in computer science · doi:10.1007/978-3-662-72243-5_25 · Cited by 1
Density-Based Evaluation Metrics in Unsupervised Anomaly Detection Contexts
Maia, R., & Antunes, C. (2021) · Lecture notes in computer science · doi:10.1007/978-3-030-85529-1_25 · Cited by 1
TSAEns: Ensemble Learning for KPI Anomaly Detection
Wang, C., Yang, T., Cui, J., Yu, L. J., Zhou, T., & Cai, Z. (2022) · Lecture notes in computer science · doi:10.1007/978-3-030-95384-3_11 · Cited by 1
Feature consistency anomaly detection method based on adversarial training deep autoencoder
Lai, C., & Jia, P. P. (2022) · Youth Academic Annual Conference of Chinese Association of Automation (YAC) · doi:10.1109/yac57282.2022.10023751 · Cited by 1
“Ref.[17] proposed a multivariable time series UnSupervised Anomaly Detection (USAD) method based on adversarial trained autoencoder.”
MethodZhai, Z., Di, Y., Wang, F., Leng, Z., Zhao, Z., & Chen, X. (2022) · International Conference on Sensing, Measurement & Data Analytics in the era of Artificial Intelligence (ICSMD) · doi:10.1109/icsmd57530.2022.10058285 · Cited by 1
“KitNet [26] 63.12 79.36 0.70 GAN-Li [27] 71.02 87.06 0.78 OmniAnomaly [4] 78.48 99.24 0.88 MTAD-GAT [28] 79.17 98.24 0.88 USAD [29] 79.49 99.12 0.88 AGCR-AE 84.86 97.79 0.91”
MethodInfluentialCollaborER: A Self-supervised Entity Resolution Framework Using Multi-features CollaborationPreprint
Ge, C., Wang, P., Lü, C., Liu, X., Zheng, B., & Gao, Y. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2108.08090 · Cited by 1
Cyber-Resilient Digital Twins: Discriminating Attacks for Safe Critical Infrastructure ControlPreprint
Homaei, M., Khazrak, I., Molano, R., Caro, A., & Avila, M. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6439880 · Cited by 4
Unsupervised anomaly detection in time-series
Audibert, J. (2021) · theses.fr (ABES) · doi:10.70675/92cd8d0bz0d6dz4c3cza4e4z859decdbbd88 · Cited by 14
Self-citationKy, J. R. (2025) · theses.fr (ABES) · doi:10.70675/6799e73bz7575z43fbz97f4z865ce6f35c4c · Cited by 3
A Problem-Oriented Taxonomy of Evaluation Metrics for Time Series Anomaly DetectionPreprint
Yang, K., Liu, J., Song, Y., Yang, S., & Zhou, Y. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6826583 · Cited by 1
Ensemble Neuroevolution-Based Approach for Multivariate Time Series Anomaly Detection
Faber, K., Pietroń, M., & Żurek, D. (2021) · Entropy · doi:10.3390/e23111466 · Cited by 26
“Moreover, for our baseline models (USAD, LSTM-VAE, CNN 1D), we present outcomes from our experiments for the SWAT dataset, in which for some cases, the results are slight different to the original result, as it required preparing our own implementation (marked as **).”
BackgroundMethodInfluentialFerrari, L. M., Hanna, G. A., Volpe, P., Ismailova, E., Brémond, F., & Zuluaga, M. A. (2021) · arXiv (Cornell University) · doi:10.48550/arxiv.2104.04546
“The network is trained using a two-phase adversarial training scheme to allow the AEs to learn how to amplify the reconstruction error as detailed in [2].”
MethodSelf-citationHierarchical Feature Fusion based Reconstruction Network for Unsupervised Anomaly Detection
Zhao, B., Nie, J., Guan, S., Wang, H., He, Z., & Gao, M. (2022) · IEEE International Conference on Emerging Technologies and Factory Automation (ETFA) · doi:10.1109/etfa52439.2022.9921590
“As a critical way to monitor the status of equipment, anomaly detection of time series data has been widely concerned in urban resource management [1], computer network intrusion detection [2][3], aerospace [4] and industrial production [5].”
BackgroundA Novel Unsupervised Anomaly Detection Approach Using Neural Transformation in Cloud Environment
Zhang, R., Chen, J., Song, Y., Shan, W., Chen, P., & Xia, Y. (2022) · Lecture notes in computer science · doi:10.1007/978-3-031-23498-9_9
Smoothing Point Adjustment-Based Evaluation of Time Series Anomaly Detection
Liu, M.-Y., Wang, Y., Xu, H., Zhou, X., Li, B., & Wang, Y. (2023) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49357.2023.10095163
Sparse and Semi-Attention Guided Faults Diagnosis Approach for Distributed Online ServicesPreprint
Shi, Y., & Zhang, L. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4485216
Multivariate Time Series Anomaly Detection in a Regularization Perspective
Guo, Q., -, J. Z., Chen, Y., & Liu, R. (2023) · International Conference on Computing and Artificial Intelligence (ICCAI) · doi:10.1145/3594315.3594655
Towards Practical Machine Learning Frameworks for Performance Diagnostics in Supercomputers
Aksar, B., Sencan, E., Schwaller, B., Leung, V. J., Brandt, J. M., Kulis, B., Egele, M., & Coskun, A. K. (2023) · doi:10.1145/3588982.3603609
“These methods include adversarially trained autoencoders [9] for isolating anomalies, graph neural networks for identifying anomalies via attention-based forecasting”
MethodEnhancing Time Series Anomaly Detection Using Discretization and Word Embeddings
Pérez, L., Costa, N., & Sánchez, L. (2023) · Lecture notes in networks and systems · doi:10.1007/978-3-031-42536-3_26
Unsupervised Tensor Based Feature Extraction From Multivariate Time Series
Matsue, K., & Sugiyama, M. (2023) · IEEE Access · doi:10.1109/access.2023.3326073
Noise-Aware Self-Supervised Denoising for Electrocardiogram Anomaly DetectionPreprint
Chen, P., Deng, M., Zhang, D., Zhou, B., & Fan, H. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4601063
Structural Health Monitoring of Similar Gantry Crane Based on Federated Learning Algorithm
Peng, Z., Zhang, Z., Zhao, X., Zhang, T., & Wu, Q. (2023) · Communications in computer and information science · doi:10.1007/978-981-99-7590-7_7
Jaewon, L. E. E., & Lee, S. (2023) · SSRN Electronic Journal · doi:10.2139/ssrn.4618363
Tong, X., Jung, W. Q., & Banning, J. F. (2023) · Annual Conference of the PHM Society · doi:10.36001/phmconf.2023.v15i1.3547
“…and identifying the underlying correlations for normalizing features based on context etc. Existing research efforts in the realm of anomaly detection cover supervised, semi-supervised (Jiang, Kao & Li, 2021) and unsupervised (Audibert, Michiardi, Guyard, Marti, and Zuluaga, 2020) approaches.”
BackgroundAttack Model for the Industrial Water Treatment Systems
Владимировна, Ф. Е., Novikova, E. S., & Saenko, I. B. (2023) · International Conference on Control in Technical Systems (CTS) · doi:10.1109/cts59431.2023.10288930
“Currently focus of the researchers is switched to the deep neural networks [20–21] and explanation of the detected anomalies [22, 23].”
BackgroundA GAN-Based Power Quality Anomaly Detection Method for Imbalanced Multivariate Time Series
Huang, J., Liu, C., Yang, Y., & Liu, Y. (2023) · IEEE International Conference on Computer and Communication Engineering Technology (CCET) · doi:10.1109/ccet59170.2023.10335146
“• USAD [9]: An anomaly detection model based on reverse training of autoencoders.”
MethodZhang, K., Li, C., Yang, Q., Lin, W., & Yuan, L. (2023) · International Conference on Information Science and Technology · doi:10.1109/icist59754.2023.10367117
“They are Isolation Forests [16], autoencoders [17], LSTM-VAE [18], DAGMM [8], and USAD [19], are mature and extensively used in the field of anomaly detection.”
MethodDetecting Anomalies in Traction Motor Bearing Using Multi-scale Segmented Autoregressive Network
Liu, Q., Tian, Y., Tang, H., Li, B., Zheng, X., & Cui, X. (2024) · Lecture notes in electrical engineering · doi:10.1007/978-981-99-9315-4_20
CAE_AD: Unsupervised Time Series Anomaly Detection Method Based on Convolutional Autoencoder
韩, 广. (2024) · Journal of Image and Signal Processing · doi:10.12677/jisp.2024.131003
Meng, Z., Zhu, X., Pan, F., & Hu, Z. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394599
Local-Adaptive Transformer for Multivariate Time Series Anomaly Detection and Diagnosis
Zhou, X., Wang, Y., Xu, H., Liu, M.-Y., & Zhang, R. (2023) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc53992.2023.10394229 · Cited by 1
“2) Baselines: We compare LAT with state-of-the-art models for multivariate time series anomaly detection, including DAGMM [19], LSTM-ED [8], Tcn-ED [27], MSCRED [5], OmniAnomaly [10], USAD [13], GDN [18] and TranAD [16].”
BackgroundMethodA Novel Semi-supervised IoT Time Series Anomaly Detection Model Using Graph Structure Learning
Song, W., Chen, P., Chen, J., Xia, Y., Li, X., Xi, Q., & He, H. (2024) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-54528-3_21
Translated Temporal Component-Enhanced Attention for Multivariate Time-Series Anomaly DetectionPreprint
Seo, M., & Kim, M. H. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4743831
Zhou, Y., Wang, J., Tang, J., Gou, C., Jiang, Z., Li, D., & Ng, S.-K. (2023) · International Conference on Artificial Intelligence of Things and Systems (AIoTSys) · doi:10.1109/aiotsys58602.2023.00049
Patch-Based Time-Series Anomaly Detection with Cross-Variable Attention
Son, J., Song, S., & Baek, J. (2024) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic60209.2024.10463377 · Cited by 1
“1 (a), they only consider the dependencies between variables within the same time point [6], [7], [8].”
BackgroundMethodMAD-SGS: Multivariate Anomaly Detection with Multi-scale Self-learned Graph Structures
Tang, J., Li, D., & Zheng, Z. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-2275-4_2
Saliency-Aware Time Series Anomaly Detection for Space Applications
Lee, S.-Y., & Woo, S. S. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-2242-6_26 · Cited by 2
Mummah, K., (NNSA), U. N. N. S. A., Jackson, D., Oakberg, J. A., Apt, K. E., & Henzl, V. (2024) · OSTI OAI (U.S. Department of Energy Office of Scientific and Technical Information) · doi:10.2172/2352690
Prediction of Anomalous Events with Data Augmentation and Hybrid Deep Learning Approach
Raihan, A. S. (2024) · The Research Repository @ WVU (West Virginia University) · doi:10.33915/etd.12347 · Cited by 1
A cautionary tale on the cost-effectiveness of collaborative AI in real-world medical applicationsPreprint
Innocenti, L., Sebastien Ourselin, A., Goh, V., Antonelli, M., & Lorenzi, M. (2024) · bioRxiv (Cold Spring Harbor Laboratory) · doi:10.1101/2024.05.27.596048
“CBL outperformed FL in all three task categories (classification, segmentation, survival), however none of these differences were statistically significant (see Table 2).”
Anodec: Time Series Anomaly Detection with Deep Embedded Clustering NetworkPreprint
Lee, S.-Y., & Kim, D. (2024) · SSRN Electronic Journal · doi:10.2139/ssrn.4862103
Extended Framework and Evaluation for Multivariate Streaming Anomaly Detection with Machine Learning
Koch, A., Petry, M. J., & Werner, M. (2024) · IEEE International Conference on Data Engineering Workshops (ICDEW) · doi:10.1109/icdew61823.2024.00025
“The model parameters are This simple reconstruction model is compared to the more complex adversarial autoencoder (USAD) from [28]. is paired with two decoders , where z t = E ( x Tt ) is the latent vector with z t ∈ R Z , Z << w .”
MethodA Multi-scale Parallel Unsupervised Model for Multivariate Time Series Anomaly Detection
Bao, J., Gao, H., Zhang, C., Jia, W., Gao, J., & Yang, T. (2024) · IFIP advances in information and communication technology · doi:10.1007/978-3-031-63223-5_18
A Transfer Learning-Based New User Recognition for Minimizing Retraining Time in Edge Deep Learning
Heo, D. H., & Kang, S. J. (2023) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci62032.2023.00031
Liang, L., Qiu, X., Zhang, Y., Guan, D., Zhang, J., & Yuan, W. (2024) · Communications in computer and information science · doi:10.1007/978-981-97-4390-2_5
Zhang, H., Liu, H., Zhang, Y., Guo, Y., Dai, H., Shao, M., & Xu, H. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5489-2_27
Deep Block Transformer for Anomaly Detection
Ishaq, M. Y., Zhou, Y., Xue, S., Raza, Q., An, Z., & Amin, M. U. (2024) · International Conference on Computer Communication and Artificial Intelligence (CCAI) · doi:10.1109/ccai61966.2024.10603098
“This approach has become increasingly relevant across a spectrum of data-driven industries such as distributed computing, the Internet of Things (IoT), robotics, and urban resource management, as noted in references [4].”
BackgroundDBPrompt: A Database Anomaly Operation Detection and Analysis via Prompt Learning
Zhong, H., Wang, J., Wang, X., Wang, X., Xiao, W., Tang, X., & Zang, L. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-5603-2_29 · Cited by 1
Ding, G., Zhu, Y., & Ren, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-981-97-7238-4_4 · Cited by 2
An Online Anomaly Detection Algorithm with Adaptive Concept Drift
Li, M. (2024) · International Conference on Communications, Information System and Computer Engineering (CISCE) · doi:10.1109/cisce62493.2024.10653010
“Therefore, it is considered normal data [9] .”
BackgroundSharma, N., & Arora, B. (2024) · International Journal of Pattern Recognition and Artificial Intelligence · doi:10.1142/s0218001424390014
Comparison of Industrial Control System Anomaly Detection Methods
Soboński, P., & Roedig, U. (2023) · doi:10.1145/3689930.3695211 · Cited by 2
Adversarial Deep Domain Adaptation Method for Unsupervised Anomaly Detection
Matsuo, Y., & Tajiri, K. (2024) · International Conference on 6G Networking (6GNet) · doi:10.1109/6gnet63182.2024.10765658
Satellite State Prediction and Maneuver Detection Analysis Using NCDEs
Lee, K., & Woo, S. S. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78189-6_15 · Cited by 2
Sun, S., Zhou, Y., Yao, S., & Xu, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0840-9_26
Adaptive Plug-and-Play Framework for Time Series Anomaly Detection with Temporal Drift
Zhong, C., Chen, X., Ma, Z., Ran, J., Shao, S., Xing, T., & Wang, J. (2024) · Lecture notes in computer science · doi:10.1007/978-981-96-0840-9_28
Yu, H. C., Sun, W., Liu, J., & Gao, P. (2024) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/cyberscitech64112.2024.00038
Meng, F., Chen, B., Zhang, X., & Zhu, S. (2024) · Asia Service Sciences and Software Engineering Conference (ASSE) · doi:10.1145/3702138.3702148
Novel Real-Time Anomaly Detection Approach for Data Analysis
Wang, H., Zhang, S., Zhang, L., Wang, Y., & Li, M. (2024) · International Conference on Data Intelligence and Cognitive Informatics (ICDICI) · doi:10.1109/icdici62993.2024.10810779
Machine Learning for Network Intrusion Detection
Zhang, Z. (2025) · Springer eBooks · doi:10.1007/978-3-030-71522-9_1631
PIMGAN: Prior-induced Masked GAN for Myocardial Infarction Anomaly Detection
Chen, J.-B., Zhou, L., Huang, X., Li, R., Wang, Z., & Fan, H. (2024) · International Symposium on Artificial Intelligence for Medicine Sciences (ISAIMS) · doi:10.1145/3706890.3706952
ISTAD: Scaled Transformer with Interactive Learning for Multivariate Time Series Anomaly Detection
Kang, J., Wan, G., Lu, J., & Huang, Y. (2024) · International Conference on Pattern Recognition and Artificial Intelligence (PRAI) · doi:10.1109/prai62207.2024.10827712
Xiang, Z., Li, Q., Luo, H., Sun, W., Li, W., Liu, X., & Zhang, Y. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-1856-9_46
Anomaly tracing of electricity information collection system based on GAN and BiLSTM
Xiao-dong, X., Li, X., Guo, H., Dai, Y., Wang, Z., & Wang, P. (2024) · International Conference on Advances in Artificial Intelligence (ICAAI) · doi:10.1145/3704137.3704191
Dynamic Soft Contrastive Learning for Time Series Anomaly Detection
Song, Y., Liu, Y., & Shu, S. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889377
“The comparison with SOTA methods includes semi-supervised methods DeepSAD [23], one-class-classification methods DROCC [24] and USAD [25], and unsupervised methods DAGMM [26], GANF [6], and MTGFlow [5].”
Deep Time Series Anomaly Detection with Local Temporal Pattern Learning
Li, Y., Wang, Y., Xu, H., & Zhou, X. (2025) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp49660.2025.10889109
“…following 20 competing methods, including LOF [33], OCSVM [34], ECOD [35], iForest [36], DIF [27], DSVDD [37], COUTA [31], GDN [10], LSTM-NDT [11], LSTM-ED [38], Omni [7], MSCRED [39], USAD [5], TcnED [40], Anomaly-former [9], TranAD [8], NeuTral [23], TS-CP2 [41], NCAD [22] and DCdetector [42].”
DBSFT: A High-Precision Database Anomaly Detection and Analysis via Task-Tune Based LLM
Zhong, H., Wang, J., Wang, X., Wang, X., Xiao, W., Tang, X., & Zang, L. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-96-2468-3_40
Advances in Deep Learning for Multivariate Time-Series Anomaly Detection
Azad, M., Raghuwanshi, S., & Jain, M. (2024) · International Conference on Communication, Control and Intelligent Systems (CCIS) · doi:10.1109/ccis63231.2024.10932064
Wang, A., Zhang, Q., Zhu, M., Chao, X., Li, J., & Bao, J. (2024) · Asia-Pacific Artificial Intelligence and Big Data Forum (AIBDF) · doi:10.1145/3718491.3718615
Time Series Anomaly Detection Algorithm Incorporating Data Augmentation in Data Scarcity Scenarios
Huang, Q. (2025) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-3-031-84228-3_39
Anomaly Detection in Multivariate Time Series Using Uncertainty Estimation
Müller, M., Ernis, G., & Möck, M. (2025) · Cognitive technologies · doi:10.1007/978-3-031-83097-6_14 · Cited by 3
Adi, A. C., Zein, A. A., & Thaher, I. A. (2024) · International Seminar on Research of Information Technology and Intelligent Systems (ISRITI) · doi:10.1109/isriti64779.2024.10963471
“For example, XGBoost, when integrated with deep learning models such as LSTMs, has demonstrated significant improvements in anomaly detection tasks [18][20].”
Vehicle Health Indicator Based on Cumulative Reconstructed Errors
Yun, J., Chu, C., Heo, J., Lim, S., bin Jeong, H., & Kim, S.-B. (2025) · Journal of Korean Institute of Industrial Engineers · doi:10.7232/jkiie.2025.51.2.127
Multimodal Anomaly Detection for Semiconductor Manufacturing Material Quality
Baek, M., & Kim, S. J. (2025) · Journal of Korean Institute of Industrial Engineers · doi:10.7232/jkiie.2025.51.2.182
Bukharev, D. A., & Sokolov, A. N. (2025) · International Russian Smart Industry Conference (SmartIndustryCon) · doi:10.1109/smartindustrycon65166.2025.10985971 · Cited by 1
DASTAD: Dual Aspect Self-supervised Transformer-based Anomaly Detection in Multivariate Time-Series
Aggarwal, K., Sowmya, K., & Ramesh, K. (2025) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-025-10300-z
KPI Anomaly Detection Method for Multi-Scale Feature Fusion in Time-Frequency Domain
Yang, J., Liu, Y., Mao, F., & Huang, J. (2025) · International Symposium on Computer Applications and Information Systems (ISCAIS) · doi:10.1109/iscait64916.2025.11010336
A Hybrid Spiking Model for Anomaly Detection in Multivariate Time Series
Zhang, W., He, P., Wang, S., Yang, F., & Liu, Y. (2025) · Expert Systems · doi:10.1111/exsy.70086 · Cited by 1
“Su et al. (2019), Zhao et al. (2020) and Audibert et al. (2020) adopted such a strategy in evaluation.”
Improving the Stability of Networks Anomaly Detection in Internet of Things
Zhao, B., Zeng, Z., & Deng, X. (2024) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn63567.2024.00052
SSAD: State Space-Based Anomaly Detection in Industrial Control Systems
Wei, Z., Lv, F., Xiao, L., Chen, X., Lv, S., & Sun, L. (2024) · International Conference on Mobility, Sensing and Networking (MSN) · doi:10.1109/msn63567.2024.00072
“For instance, models based on CNN [4], RNN [5], GAN [6]– [8], GNN [9], [10], have been utilized to address this issue.”
AnomalyTK: A Multivariate Time Series Anomaly Detection Method
Xiao, T., & Zeng, F. (2025) · International Conference on Sensor-Cloud and Edge Computing System (SCECS) · doi:10.1109/scecs65243.2025.11065321
“We report the results of AnomalyTK on the two real-world datasets introduced above and compare them with six previously proposed models: LSTM-VAE [15], DAGMM [16], OmniAnomaly [17], USAD [18], GDN [19], and ANOMALY-BERT [7].”
TGM: An Industrial Sensor Network Anomaly Detection
Wang, T., Zou, C., Liu, Y., Zhou, L., & Wang, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9946-9_34
Rethinking Time Series Anomaly Detection: A Scalable Transformer-Based Framework for Large Contexts
Hoh, M., Schaub, H., Leuze, N., & Schöttl, A. (2025) · International Conference on Control, Automation and Robotics (ICCAR) · doi:10.1109/iccar64901.2025.11072949
A Network Traffic Anomaly Detection Method Based on BLTranAD-NR
Fan, H., Wu, S., Wan, Y., Tan, X., Sun, D., Ma, H., Zhang, C., & Dong, Y. (2025) · Communications in computer and information science · doi:10.1007/978-981-96-9986-5_39
Towards a New Categorization of Models for Multivariate Time Series Anomaly Detection
Alves, B., Pinho, A. J., & Gouveia, S. (2025) · Lecture notes in computer science · doi:10.1007/978-3-031-99568-2_29 · Cited by 1
Toward Anomaly Explanations in Water Treatment Systems
Tushkanova, O. N., Novikova, E. S., & Fedorchenko, E. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-2724-0_22
Xi, Q., Li, X., Chen, P., Chen, J., Ren, J., Song, W., & He, H. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-93257-1_7
A Dual-Branch Incremental Learning Framework for Industrial Production Anomaly Detection
Xu, X., Qiu, Y., Jia, Q., Zhu, Q., Zhu, P., Zhao, D., Shang, X., & Sheng, N. (2025) · International Conference on Machine Learning and Intelligent Systems Engineering (MLISE) · doi:10.1109/mlise66443.2025.11100180
Compatible Unsupervised Anomaly Detection with Multi-Perspective Spatio-Temporal Learning
Chen, T., Zheng, B., Liu, S., Fan, Z., Xu, Z. X., Yan, L., Zeng, K., Ye, T., & Zhou, X. (2025) · IEEE International Conference on Data Engineering (ICDE) · doi:10.1109/icde65448.2025.00303 · Cited by 1
Anomaly Detection Model Based on Anomaly Representation Reinforcement and Path Iterative Modeling
Chen, X., Zhu, W., Zeng, Z., Qiu, Z., & Xiao, R. (2025) · Concurrency and Computation Practice and Experience · doi:10.1002/cpe.70245 · Cited by 1
Xi, Q., Li, X., Chen, P., Chen, J., Niu, X., & Xu, L. (2025) · The Journal of Supercomputing · doi:10.1007/s11227-025-07717-6
“USAD [24]: The core idea is to learn the distribution patterns of the data and then label samples that deviate from this pattern as anomalies.”
Amad: Automasked Attention for Unsupervised Multivariate Time Series Anomaly DetectionPreprint
Huang, T., Li, G., & Li, Y. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5405068
Wang, G., Li, Q., Wang, Q., Alsolai, H., & Jiang, X. (2025) · IEEE Transactions on Consumer Electronics · doi:10.1109/tce.2025.3608449
“Inspired by GANs, Audibert et al. [33] proposed the USAD method for multivariate time-series anomaly detection.”
Xin, R., Gao, F., Gong, S., & Chen, P. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5498415
Deep Time Series Anomaly Detection and Its Application in Track Anomaly Detection
王, 玉. (2025) · Journal of Image and Signal Processing · doi:10.12677/jisp.2025.144039
Frequency-Domain Dual Masking for Enhanced Time Series Anomaly Detection
Chen, J., & Zhang, S. (2025) · International Conference on Computer Information Science and Application Technology (CISAT) · doi:10.1109/cisat66811.2025.11181982
“The inherent complexity of sensor interrelationships leads to strong correlations and dynamic interdependencies in multivariate time series [1].”
Maru, C., Oguchi, M., & Kobayashi, I. (2025) · Lecture notes in computer science · doi:10.1007/978-3-032-05962-8_6
Tian, Z., Kalidindi, R. V., & Gurusamy, M. (2025) · IEEE Conference on Communications and Network Security · doi:10.1109/cns66487.2025.11194999
Mender: Multi-dimensional Time Series Data Cleaning Based on Dynamic Patterns
Li, C., Ma, C., Li, C., & Meng, X. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3462-3_1 · Cited by 1
Phungtua-Eng, T., Arima, N., & Yamamoto, Y. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3456-2_2
Metadata
- Authors
- Audibert, J., Michiardi, P., Guyard, F., Marti, S., & Zuluaga, M. A.
- Affiliations
- EURECOM (FR)
- EURECOM, Biot, France
- Orange (France) (FR)
- Venue
- Proceedings of the 26th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining
- Publisher
- ACM
- Published
- 2020-08-20
- Pages
- 3395-3404
- OpenAlex
- W3081497074
- Cited by
- 1,094
- References
- 20
- Citations by year
- 2026: 281 · 2025: 266 · 2024: 256 · 2023: 170 · 2022: 84 · 2021: 37
- FWCI
- 27.79
- Type
- conference paper
- Language
- en
- Open access
- hybrid
- doi.org
- Licence
- Locations
- ACM SIGKDD Conference on Knowledge Discovery and Data Mining (KDD) (publishedVersion, cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Computer Networks and Communications › Software System Performance and Reliability
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- unsupervised anomaly detection, multivariate time series, adversarial autoencoder, network anomaly detection, orange, scalability, robustness
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.