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 801–900 of 1,000
Jia, Y., Li, F., Zhang, J., & Li, J. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3459-3_1
Unsupervised Transformer-Based Anomaly Detection for IoT Networks
Kołpa, P., Adewole, K. S., Persson, J., & Karlsson, F. (2025) · International Conference on Future Internet of Things and Cloud (FiCloud) · doi:10.1109/ficloud66139.2025.00032
Anomaly Detection for Multivariate Industrial Time Series Based on Consistency Models
Fang, B., Li, Y., & Liu, Z. (2025) · IEEE International Conference on Software Quality, Reliability and Security Companion (QRS-C) · doi:10.1109/qrs-c65679.2025.00057
Edge-AD: An Edge-Oriented Anomaly Detection Approach with Gated Fusion and Dynamic Thresholding
Wang, C., Wang, T., Chu, Y., Yang, X., & Su, Z. (2025) · International Conference on Internet of Things, Artificial Intelligence and Mechanical Automation (IoTAIMA) · doi:10.1109/iotaima66468.2025.11212741
“The comparison methods include representative time series anomaly detection models, such as: LSTM-VAE [8], USAD [9] and AnomalyTransformer [10].”
Time-Frequency Feature Regularized Autoencoder for Atrial Fibrillation Anomaly Detection
Gao, S., Haoyi, F., Huang, X., Pan", Y., Zhou, L., & Wang, Z. (2025) · International Conference on Simulation, Modeling and Big Data (SMBD) · doi:10.1145/3768740.3768783
Unsupervised Time Series Anomaly Detection Based on Conditional Variational Auto-Encoder
Gui, J., Li, Y., & Zhang, D. (2025) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon58223.2025.11221423
“Audibert et al. [13] proposed the UnSupervised Anomaly Detection (USAD), which is based on adversarial training and aims to increase the reconstruction error for anomalous inputs.”
Multivariate Time Series Anomaly Detection in Cyber-Physical Systems Using Sparse Attention
Li, Y., Gui, J., & Zhang, D. (2025) · Annual Conference of the IEEE Industrial Electronics Society (IECON) · doi:10.1109/iecon58223.2025.11221241
“RNN-based methods such as OmniAnomaly [2] and InterFusion [3] leverage temporal dependencies for sequence reconstruction, while GAN-based methods like USAD [4] and BeatGAN [5], enhance anomaly sensitivity via adversarial training.”
MODIFICATION OF THE LIGHTWEIGHT STREAM CIPHER ALGORITHM CHACHA20
Bakyt, M., Moldamurat, K., Kalmanova, D. М., Abdirashev, O. K., & Konyrkhanova, A. A. (2025) · Bulletin of Shakarim University Technical Sciences · doi:10.53360/2788-7995-2025-3(19)-3
Adaptive Hierarchical Attention for Multivariate Time Series Anomaly Detection
You, X., Guo, X., Wang, B., & Wang, C. (2025) · Annals of Data Science · doi:10.1007/s40745-025-00662-4
An, J., Cheng, X., Zhang, S., Tan, Y., & Xu, W. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-4381-6_30 · Cited by 1
Robust Anomaly Detection with Spatio-temporal Representation Learning for Multivariate Time Series
Huang, S., Wu, X., Chen, J., Chen, N., Qin, H., Deng, T., & Wu, F. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11227305
Saliency Time-Series Anomaly Detection Service for AIOps
Zhang, L., Huang, H., Sun, X., Wang, R., Lifeng, Z., Wang, H., Zhu, W., & Jiang, X. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228205
(2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228430
“To address these limitations, reconstruction-based methods have garnered attention for their effectiveness in anomaly detection [8], [9].”
Time Series Anomaly Detection Based on Contrastive Learning
Heng, H., & Zhang, S. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11229394
Jach, A. (2025) · Artificial Intelligence Review · doi:10.1007/s10462-025-11371-y
“The challenge of anomaly detection in multivariate time series has been a focus of research for various scholars, including Audibert et al. ( 2020 ).”
Self-Supervised State-Space Model for Real-Time Traffic Accident Forecasting Using eKAN Networks
Tan, X., Yan, S., Zhou, S., & Zhao, M. (2025) · Transportation Research Record Journal of the Transportation Research Board · doi:10.1177/03611981251381308
Faro: A Scalable and Reliable Outage Detection Algorithm for IoT Mobile Virtual Network Aggregators
Milani, M., Vomhoff, V., Bega, D., Gramaglia, M., Geißler, S., Karsai, C., & Serrano, P. (2025) · Proceedings of the ACM on Networking · doi:10.1145/3768982
LiST-CFD: Lightweight Spatio-Temporal Convolutional Fault Detection for Spacecraft
Zhao, J., Wang, S., Li, S., Qin, P., & Liu, C. (2025) · IFAC-PapersOnLine · doi:10.1016/j.ifacol.2025.11.506
Power System API Anomaly Detection Method Based on Temporal-Semantic Information
Li, K., Cao, Y., Wang, W., Zhang, H., Zhou, J. H., & Li, H. (2025) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann66429.2025.11257707 · Cited by 1
“The USAD[13] method uses an autoencoder with two decoders with an adversarial game-style training framework.”
SPTAD: Transformer with Sinusoidal Prototype Guidance for Time Series Anomaly Detection
Li, Y., Wen, Z., Lin, M., Zhu, J., Liu, S., Hu, Z., & Zhu, M. (2025) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann66429.2025.11257686
“We extensively compare SPTAD with 6 baselines, including traditional machine learning method LOF [6] and deep learning methods AE-LSTM [12], THOC [13], USAD [4], VAEAT [14], and [15].”
The Multi-Modal Anomaly Detection Method for Microservices Based on VGAE-Transformer
Shao, C., Zhou, X., Zhang, Z., & Tao, C. (2025) · International Conference on Advanced Algorithms and Neural Networks (AANN) · doi:10.1109/aann66429.2025.11257637
“USAD [6] : This model introduces an anomaly detection method for multivariate time series data using an architecture based on autoencoders (AE), enhanced with adversarial training techniques.”
Xiao, Y., Wang, Z., Yan, T., Li, W., Wu, D., & Ma, J. (2025) · IEEE International Conference on Cyber Security and Cloud Computing (CSCloud) · doi:10.1109/cscloud66326.2025.00046 · Cited by 1
“Notable instances include Donut for seasonal KPI monitoring, DAGMM coupling AE with GMM energy, USAD with adversarial training, and MSCRED using multi-scale correlation signatures [17, 18, 36, 37].”
Towards Real-Time Detection of Anomalous Behavior in Crowds from Accelerometer Time Series
Kor, B., Gaikwad, B., Patra, A., & Miller, E. L. (2025) · European Signal Processing Conference (EUSIPCO) · doi:10.23919/eusipco63237.2025.11226395
“We review two state-of-the-art models, USAD [12] and TranAD [9] which address challenges like temporal dependencies, multivariate correlations, and subtle anomaly detection in complex patterns.”
Industrial anomaly detection via curriculum-based deep learning
Dube, D. C., & Akar, M. (2025) · Applied Intelligence · doi:10.1007/s10489-025-07032-w
Invariant Rules-Based Anomaly Detection in Industrial Control Systems
Liu, K., Xie, Y., Xie, S., Wang, X., Wang, H., Li, Z., Pan, Z., & Sun, L. (2025) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana66698.2025.00013 · Cited by 1
An Incremental Learning-Based Anomaly Detection Model for High-Dimensional Time Series
Chen, Y., Ren, B., Gao, C., & Ma, S. (2025) · International Conference on Networking and Network Applications (NaNA) · doi:10.1109/nana66698.2025.00010
Sparse Transformer for Anomaly Detection with Association Discrepancy
Shrestha, S., Zhang, Y., Liu, H., & Silwal, A. (2025) · IEEE International Conference on Tools with Artificial Intelligence (ICTAI) · doi:10.1109/ictai66417.2025.00086 · Cited by 1
LSGNSF: A Graph-Based Time Series Anomaly Detection Algorithm
Zhang, C., Dong, Y., Zhang, Y., Li, J., Fan, H., Sun, D., & Ma, H. (2025) · Lecture notes in computer science · doi:10.1007/978-981-96-9818-9_18
Lai, S., Cheung, T.-H., Zhao, J., FUNG, K. C., Xue, K., Lyu, Z., Goshu, H. L., & Lam, K. (2025) · SSRN Electronic Journal · doi:10.2139/ssrn.5787564
SmartPP: Speeding Up Diffusion-Based Time Series Anomaly Detection via Smart Patch Parallelization
Liu, S., Ma, C., Chen, L., Wang, Y., Shi, X., & Zhu, W. (2025) · IEEE International Symposium on Parallel and Distributed Processing with Applications (ISPA) · doi:10.1109/ispa67752.2025.00080
“Audibert et al. [15] proposed an encoder-decoder architecture named USAD consisting of one encoder and two decoders (AE1 and AE2).”
Park, T., Kang, C.-W., Kim, H.-S., & Lee, D. (2025) · Journal of Digital Contents Society · doi:10.9728/dcs.2025.26.11.3209
Identifying seismic precursors from groundwater radon anomalies based on machine learning
Hui, L. I. U., Hong-biao, G. U., Yu-xia, Y. A. O., & Ming-gui, L. U. (2025) · Bulletin of Mineralogy Petrology and Geochemistry · doi:10.3724/j.issn.1007-2802.20250133
Zhang, Z., Chen, J., Jin, G., & Guo, Z. (2025) · IEEE Journal of Biomedical and Health Informatics · doi:10.1109/jbhi.2025.3647132 · Cited by 1
“For instance, Audibert et al. [31] proposed USAD, which performs anomaly detection based on the reconstruction error of an adversarial autoencoder and demonstrates stable robustness across different noise injection ratios in multivariate time-series experiments.”
Decomposable Multi-Scale Graph Networks for Time Series Anomaly Detection
Wang, C., Ding, F., Li, Z., Liu, Y., & Guo, D. (2025) · International Conference on New Trends in Computational Intelligence (NTCI) · doi:10.1109/ntci67886.2025.11308531
MambaGuard: A Hybrid Framework for Unsupervised Anomaly Detection in IIoT Networks
Xiong, F., Mahanti, A., & Ding, N. (2025) · IEEE International Conference on Smart Internet of Things (SmartIoT) · doi:10.1109/smartiot66867.2025.00019
“Audibert et al. [18] developed USAD, using dual autoencoders with adversarial training for unsupervised anomaly detection.”
Wang, X., Liu, K. J. R., Li, S., Pan, Z., Lv, S., & Sun, L. (2026) · Communications in computer and information science · doi:10.1007/978-981-95-2581-2_32
PP-MTAD: Privacy-Preserving and Efficient Multivariate Time Series Anomaly Detection
Su, M., Liu, J.-N., He, K., Weng, J., Yang, A., Liu, X., & Weng, J. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-6203-9_10
Liang, Y., Zhang, T., Wang, X., Pan, L., & Xie, T. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-4445-5_31
Causal-Bayesian Modeling for Risk-Aware Resilience in Industrial Cyber-Physical Systems
Ghazi, Y., Tabaa, M., Ennaji, M., & Zaz, G. (2025) · doi:10.1109/icm66518.2025.11322488
Guo, Z., Huang, W., Chen, Y., Wang, D., Gong, C., & Lian, Z. (2025) · International Conference on Artificial Intelligence and Automation Control (AIAC) · doi:10.1109/aiac68175.2025.11332365
He, S., Feng, K., Meng, K., Guo, M., Liang, D., & Sharma, P. K. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-025-02913-5
Multivariate Time Series Anomaly Detection Based on Time-Domain and Frequency-Domain Fusion
Xu, J., Liu, H., & Xu, J. (2025) · Industry science and engineering. · doi:10.62381/i255a05
Multimodal Unsupervised Anomaly Detection for High Performance Computing Systems
Wang, L., & Li, Y. (2025) · International Conference on Machine Learning and Computer Application (ICMLCA) · doi:10.1109/icmlca66850.2025.11336692
Owusu, E., Danlard, I., Klogo, G. S., Boateng, K. O., & Akowuah, E. K. (2026) · Journal of Computer Networks and Communications · doi:10.1155/jcnc/7289868
Gu, X., Sun, Y., Han, A., Bi, X. J., Bi, K., Ying, S., & Ji, H. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-5716-5_42
MSADNet: Multi-Scale Adaptive Dual Attention Network for Multivariate Time Series Anomaly Detection
Lyu, X., Yang, Y., Zhang, C., & Huang, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342760
PRAD-Net: Periodic Reorganization Anomaly Detection Network using Anomaly Injection Strategy
Lu, H., Li, X., & Ning, Z. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342509
S-DGAT: A Spatially Enhanced Dynamic Graph Attention Network for Multi-Level Anomaly Detection
Lu, Y., Chen, Z., Xu, Y., Gu, S., & Jin, X. (2026) · IEEE Access · doi:10.1109/access.2026.3658935
Zhang, Y., Zhuang, Z., Qi, Q., Sun, H., Zhu, S., Fu, X., & Wang, J. (2025) · IEEE Symposium on Reliable Distributed Systems (SRDS) · doi:10.1109/srds69199.2025.00043
Xu, T., Ren, M., Yang, K., Xu, J. T., & Zeng, X. L. (2025) · IEEE International Conference on Bioinformatics and Biomedicine (BIBM) · doi:10.1109/bibm66473.2025.11356095 · Cited by 1
MARPP: Memory-Augmented Reconstruction for Pseudo-Periodic Time Series Anomaly Detection
Zuo, Y., Qu, M., Shang, Z., Zhang, L., & Gao, X. (2026) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom69009.2026.11360789
Lee, S., Park, J., Han, Y.-M., Kim, B.-H., Bae, Y.-S., & Jeong, J. (2026) · International Conference on Ubiquitous Information Management and Communication (IMCOM) · doi:10.1109/imcom69009.2026.11360909
An Empirical Evaluation of Multivariable Anomaly Detection Models for CNC Machine
Ju, H.-R., Jeon, W., Rhee, S., Jung, M., & Yoo, N.-H. (2025) · International Conference on Soft Computing & Machine Intelligence (ISCMI) · doi:10.1109/iscmi67495.2025.11358583
Dgaad: a novel attention-based model for HPC anomaly detection
Gao, X., Wang, Y., Dong, H. H., Wang, H., Li, Z., Yang, X., & Shang, J. (2026) · The Journal of Supercomputing · doi:10.1007/s11227-026-08257-3
Chang, S., Lin, Q., Mao, J., Yuan, M., & Huo, Y. (2025) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom66490.2025.00021
Costa, N., Lobo, A., Pina, S. R. S., Franco, F. J. G., Humphrey, A., Abbasi, A., Rodrigues, R., Fernandes, D., Mehrbod, N., Alves, M., et al. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6206936
Zeng, Z., Wang, X., Xu, L., Ye, X., Hu, J. W., Kumbhar, F. H., & Dev, K. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3663198 · Cited by 4
“…with a convolutional autoencoder; OmniAnomaly [11], which uses stochastic recurrent networks with variational inference to model uncertainty; USAD [12], which trains two autoencoders adversarially to amplify reconstruction errors; and GDN [13], which learns a directed graph to model intervariable…”
Kong, J., Gu, W., Jiang, M., & Tao, X. (2026) · International Journal of Machine Learning and Cybernetics · doi:10.1007/s13042-026-02990-0
Hu, W., & Zhao, C. (2025) · International Conference on Computer, Big Data and Artificial Intelligence (ICCBD+AI) · doi:10.1109/iccbdai66607.2025.11387828
Unsupervised Abnormal Stop Detection for Long-Distance Coaches With Low-Frequency GPS
Deng, J., Xu, J., Pang, J., Sabir, M. A., & Yu, H. (2026) · IEEE Transactions on Intelligent Transportation Systems · doi:10.1109/tits.2026.3659471
“• Unsupervised Anomaly Detection (USAD): USAD employs a dual-decoder architecture with adversarial training to learn the boundary between normal and anomalous behavior [33].”
Advancing CNNs for Time Series Anomaly Detection: A Multi-Scale Contrastive Learning Framework
Gu, H., Xiong, H., Dai, Y., Xie, Z., He, Z., Wang, X. S., & Li, J. (2026) · IEEE International Conference on Big Data and Smart Computing (BigComp) · doi:10.1109/bigcomp68355.2026.00013
Gong, L., & Zhang, C. (2026) · International Conference on Consumer Electronics and Computer Engineering (ICCECE) · doi:10.1109/iccece69169.2026.11399773
Mansur, T. A. (2025) · IEEE International Conference on Innovations in Engineering and Next-Generation Technologies for Sustainability (ICINVENTS) · doi:10.1109/icinvents64613.2025.11401405
Park, J., & Oh, H. (2025) · IEEE ... International Conference on Data Mining workshops · doi:10.1109/icdmw69685.2025.00190
“Adversarial and probabilistic methods (TranAD [16], Omni-Anomaly [17], USAD [18], TadGAN [19], Donut [20]) provide robustness and uncertainty estimates, but suffer from unstable training and high inference latency.”
Anomaly Detection in Gas Sensor Data Using LSTM Autoencoder and Latent Space Analysis
Ahmadi, M., Izidorio, F. M., Igrejas, G., CEDRI, P. R., & Lopes, R. P. (2026) · IEEE World Symposium on Applied Machine Intelligence and Informatics (SAMI) · doi:10.1109/sami68106.2026.11420410
LCDTwin: LLM-Driven Contextual Digital Twin for Actuator-Sensor Correlation in ICS
Kim, Y., Heo, W., Woo, E., & Shin, D. (2025) · International Conference on Robotics, Automation and Artificial Intelligence (RAAI) · doi:10.1109/raai67517.2025.11423321 · Cited by 1
Yang, C., Li, X., Xu, K., Lin, X., & Fu, G. (2026) · Scientific Reports · doi:10.1038/s41598-026-43236-x
Tian, H., Shi, H., Wang, L., Song, B., Tao, Y., & Yang, Y. (2026) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2026.3667392
“Audibert et al. [18] proposedanencoder–decoder architectureleveraginggenerative adversarial networks principles to enhance the detectability of weak faults.”
Adaptive malicious user detection and interpretability analysis for mobile crowdsensing systems
Wang, J., Shen, Y., & Zhao, G. (2026) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2026.104477
Multi-Scale Adaptive Attention for Time Series Anomaly Detection
Lee, W., & Ye, T. (2025) · Asia Conference on Machine Learning and Computing (ACMLC) · doi:10.1145/3772673.3772696 · Cited by 1
“We compare against multiple state-of-the-art methods including LSTM-AE [10], DAGMM [23], USAD [1], TranAD [17], and recent attention-based approaches.”
Surprised by Attention: Predictable Query Dynamics for Time Series Anomaly Detection
Özer, K.-K., Ebeling, R., & Enzweiler, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37685-5_13
Fan, Y., Lin, W., Chen, K., Wang, X., Yang, J., & Qiao, Y. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3674919
“MSCRED [36] and OmniAnomaly [15] are early influential frameworks for multivariate reconstruction-based detection, while USAD [37] improves stability via adver-sarially inspired training.”
Zheng, H., Song, Y., Liu, K., & Wang, F. (2025) · IEEE PES Innovative Smart Grid Technologies - Asia (ISGT Asia) · doi:10.1109/isgtasia63446.2025.11431539
Zheng, H., Song, Y., Liu, K., & Liu, X. (2025) · IEEE PES Innovative Smart Grid Technologies - Asia (ISGT Asia) · doi:10.1109/isgtasia63446.2025.11431342
Zhong, Z., Fu, R., Ma, M., Zhang, S., Sun, Y., Bansal, C., & Pei, D. (2026) · IEEE Transactions on Services Computing · doi:10.1109/tsc.2026.3676262 · Cited by 8
Чернова, А. С., Meshchaninov, F. P., Zhevnenko, D. A., & Горнев, Е. С. (2025) · Doklady Mathematics · doi:10.1134/s1064562425700644
Akhtar, N., & Rana, A. (2026) · Research Square · doi:10.21203/rs.3.rs-9133369/v1
Kenawy, S., Alhussan, A. A., Khafaga, D. S., Mattar, E. A., Zaman, S., & Eid, M. M. (2026) · Scientific Reports · doi:10.1038/s41598-026-41343-3
An Innovative Model for Solving the Identical Shortcut Problem in Anomaly Detection of AIOps
Luo, H., Sun, Y., Deng, H., Ma, J., Huang, J., & Yang, G. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8420-8_39
A Novel Dynamic Spatio-Temporal Collaborative Model for Multivariate Time Series Anomaly Detection
Yin, J., Bian, A., Liu, K., Chen, P., Li, X., & Chang, Y. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-21171-2_26
Heterogeneous Time Series Anomaly Detection in Cyber-Physical Systems with VAEM-LSTMs
Patel, L., & Hossain‐McKenzie, S. (2025) · International Conference on Machine Learning and Applications · doi:10.1109/icmla66185.2025.00040
“Last, there is some literature on adversarial methods for reconstruction-based detection [23], [24].”
李, 新. (2026) · Advances in Applied Mathematics · doi:10.12677/aam.2026.154147
You, P., Chen, P., Xia, Y., Li, X., Bian, A., Zeng, S., & Gao, H. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-21171-2_30
Topology-Enhanced Graph Attention Network for Anomaly Detection in IIoT Domain
Xue, R., Ding, W., Chen, C., Yu, Q., YANG, Y., Zhang, H., & Guo, J. (2026) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-032-21171-2_27
Teng, S., Chen, L., Stojmenović, M., & Ma, C. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8402-4_31
Timed automata learning from time series
Cornanguer, L. (2023) · theses.fr (ABES) · doi:10.70675/2921b612z4885z4ca2za9adz5337eb033d46
Data quality issues in mobile crowdsensing environments
Mehanna, S. (2023) · theses.fr (ABES) · doi:10.70675/2452380az1855z42a4za842z7a0b57466bb3 · Cited by 1
Mayaki, M. Z. A. (2024) · theses.fr (ABES) · doi:10.70675/e8e2614az79ffz4901z9c79ze9f9889ba9c4
A data mining perspective on explainable AIOps with applications to software maintenance
Remil, Y. (2023) · theses.fr (ABES) · doi:10.70675/e9f55171z8c4bz4857zb3e9ze9cd021af653 · Cited by 5
Dual-domain transformer with co-attention mechanism for time series anomaly detection and diagnosis
Choi, H.-J., Ahn, W. J., Dashdorj, Z., Altangerel, E., Lim, M.-T., & Kang, T. (2026) · Multimedia Tools and Applications · doi:10.1007/s11042-026-21532-y
Semi-supervised deep learning for robust anomaly detection in smart manufacturing systems
Le, T. (2024) · theses.fr (ABES) · doi:10.70675/19d23228zf030z4df7za3abz596d36577818
Temporal Conditional Score Network for Multivariate Time Series Anomaly Detection
Hao, Z., Xu, W., Zhang, X., Yazidi, A., & Yu, K. (2026) · IEEE Internet of Things Journal · doi:10.1109/jiot.2026.3681780
“…the TCSN to recent start-of-the-art anomaly detection methods, including various generative models such as adversely trained autoencoders ( USAD [17]), variational autoencoders ( LSTM-VAE [16]), Gaussian mixture-based model ( DAGMM [14]), flow-based model ( GANF [4]), and di ff ussion-based model…”
Benefit From Noise: Detecting Time-Series Anomaly by Distinguishing Prior and Posterior Noises
Xing, S., Niu, J., Ren, T., & Rodrigues, J. J. P. C. (2026) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2026.3682883
“Generation-based methods [5], [15], [16], [17], [18], [19], [20] compute anomaly scores based on the deviations between real data and generated data (from reconstruction or prediction models), leveraging the model’s ability to capture and reproduce normal patterns.”
Time–Frequency Correlation-Aware Few-Shot Learning for Time-Series Anomaly Detection
Xi, L., Li, R., Liu, H., Chen, C., & Cheng, Y. (2026) · IEEE Sensors Journal · doi:10.1109/jsen.2026.3684334
“Audib-ert et al. [18] proposed a fast and stable method called unsupervised anomaly detection (USAD), adopting two decoders to calculate reconstruction errors, effectively addressing issues related to the strong generalization capabilities of AEs.”
Zhang, A., Xu, P., & Yeo, C. K. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461681
Peng, S., Han, Y., Liu, L., Li, J., Li, R., Gu, Z., Liu, J., & Chu, X. (2026) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2026.3683936 · Cited by 1
Future Context Modeling for Time Series Anomaly PredictionPreprint
Zhao, S., Wang, W., Yu, Z., Xu, H., Wen, Q., Wang, G., Liu, X., & Pang, G. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.6630215
张, 之. (2026) · Advances in Applied Mathematics · doi:10.12677/aam.2026.154184
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.