Unsupervised Anomaly Detection With LSTM Neural Networks
Open accessThe DOI matches its Crossref record; 40 of the 40 references it cites were found in a registry or an index.
Abstract
We investigate anomaly detection in an unsupervised framework and introduce long short-term memory (LSTM) neural network-based algorithms. In particular, given variable length data sequences, we first pass these sequences through our LSTM-based structure and obtain fixed-length sequences. We then find a decision function for our anomaly detectors based on the one-class support vector machines (OC-SVMs) and support vector data description (SVDD) algorithms. As the first time in the literature, we jointly train and optimize the parameters of the LSTM architecture and the OC-SVM (or SVDD) algorithm using highly effective gradient and quadratic programming-based training methods. To apply the gradient-based training method, we modify the original objective criteria of the OC-SVM and SVDD algorithms, where we prove the convergence of the modified objective criteria to the original criteria. We also provide extensions of our unsupervised formulation to the semisupervised and fully supervised frameworks. Thus, we obtain anomaly detection algorithms that can process variable length data sequences while providing high performance, especially for time series data. Our approach is generic so that we also apply this approach to the gated recurrent unit (GRU) architecture by directly replacing our LSTM-based structure with the GRU-based structure. In our experiments, we illustrate significant performance gains achieved by our algorithms with respect to the conventional methods.
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.
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 3×
“Hence, we use the LSTM architecture [18] to obtain a fixedlength vector representation for each Xi as we previously introduced in [26].”
BackgroundMethodLIBSVM: A library for support vector machines
Chang, C.-C., & Lin, C.-J. (2011) · ACM Transactions on Intelligent Systems and Technology · doi:10.1145/1961189.1961199 · Cited by 40,918
UCI Machine Learning Repository
Asuncion, A. (2007) · Medical Entomology and Zoology · Cited by 25,373
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 10×
“, an anomaly is an event, which cannot be predicted from the past nominal data [1].”
BackgroundMethodInfluentialEmpirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 4×
“Moreover, since our approach is generic, we also apply it to the recently proposed GRU architecture [21] in our experiments.”
BackgroundMethodInfluentialLearning long-term dependencies with gradient descent is difficult
Bengio, Y., Simard, P., & Frasconi, P. (1994) · IEEE Transactions on Neural Networks · doi:10.1109/72.279181 · Cited by 8,542 · cited 1×
“However, since the basic RNN architecture does not have control structures (gates) to regulate the amount of information to be stored [16], [17], a more advanced RNN architecture with several control structures, i.”
BackgroundThe use of the area under the ROC curve in the evaluation of machine learning algorithms
Bradley, A. P. (1997) · Pattern Recognition · doi:10.1016/s0031-3203(96)00142-2 · Cited by 7,217 · cited 2×
“, also known as AUC, is a well-known performance measure for anomaly detection tasks [42].”
BackgroundMethodGreff, K., Srivastava, R. K., Koutník, J., Steunebrink, B. R., & Schmidhuber, J. (2015) · arXiv · doi:10.48550/arxiv.1503.04069 · Cited by 7,073
Greff, K., Srivastava, R. K., Koutnik, J., Steunebrink, B. R., & Schmidhuber, J. (2017) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2016.2582924 · Cited by 6,955 · cited 3×
“, the LSTM architecture without peephole connections [17].”
BackgroundEstimating the Support of a High-Dimensional Distribution
Schölkopf, B., Platt, J. C., Shawe-Taylor, J., Smola, A. J., & Williamson, R. C. (2001) · Neural Computation · doi:10.1162/089976601750264965 · Cited by 6,168 · cited 10×
“4) Through an extensive set of experiments involving real and simulated data, we illustrate significant performance improvements achieved by our algorithms with respect to the conventional methods [6], [7], [10].”
BackgroundMethodInfluential
Cited by
Deep Learning for Anomaly Detection: A Survey
Chalapathy, R., & Chawla, S. (2019) · arXiv · doi:10.48550/arxiv.1901.03407 · Cited by 1,240
Deep Learning for Time Series Anomaly Detection: A Survey
Zamanzadeh Darban, Z., Webb, G. I., Pan, S., Aggarwal, C., & Salehi, M. (2025) · ACM Computing Surveys · doi:10.1145/3691338 · Cited by 613
A survey on anomaly detection for technical systems using LSTM networks
Lindemann, B., Maschler, B., Sahlab, N., & Weyrich, M. (2021) · Computers in Industry · doi:10.1016/j.compind.2021.103498 · Cited by 445
Deep Semi-Supervised Anomaly Detection
Ruff, L., Vandermeulen, R. A., Görnitz, N., Binder, A., Müller, E., Müller, K.-R., & Kloft, M. (2019) · arXiv · doi:10.48550/arxiv.1906.02694 · Cited by 388
Unsupervised Deep Anomaly Detection for Multi-Sensor Time-Series Signals
Zhang, Y., Chen, Y., Wang, J., & Pan, Z. (2021) · IEEE Transactions on Knowledge and Data Engineering · doi:10.1109/tkde.2021.3102110 · Cited by 312
Vibration-based anomaly detection using LSTM/SVM approaches
Vos, K., Peng, Z., Jenkins, C., Shahriar, M. R., Borghesani, P., & Wang, W. (2022) · Mechanical Systems and Signal Processing · doi:10.1016/j.ymssp.2021.108752 · Cited by 233
Anomaly Detection for In-Vehicle Network Using CNN-LSTM With Attention Mechanism
Sun, H., Chen, M., Weng, J., Liu, Z., & Geng, G. (2021) · IEEE Transactions on Vehicular Technology · doi:10.1109/tvt.2021.3106940 · Cited by 197
“LSTM is an improved RNN that can successfully resolve the long-term dependence of the original RNN. LSTM has performed well in speech recognition, text processing and time series prediction in recent years [22].”
BackgroundAnomaly detection using edge computing in video surveillance system: review
Patrikar, D. R., & Parate, M. R. (2022) · International Journal of Multimedia Information Retrieval · doi:10.1007/s13735-022-00227-8 · Cited by 177
“In [28], the difference between the actual and predicted spatiotemporal characteristics of the feature descriptor is calculated to detect the anomaly [73].”
BackgroundMethodNavigating the metric maze: a taxonomy of evaluation metrics for anomaly detection in time series
Sørbø, S., & Ruocco, M. (2024) · Data Mining and Knowledge Discovery · doi:10.1007/s10618-023-00988-8 · Cited by 58
“…al. 2022; Dai et al. 2022; Schmidl et al. 2022; Campos et al. 2021; Bhatia et al. 2021; Li et al. 2021b; Huang et al. 2020; Goodge et al. 2020; Braei and Wagner 2020; Zhang et al. 2020; Ergen and Kozat 2020; Wang et al. 2019; Kieu et al. 2019; Zhou et al. 2019; Pang et al. 2019; Park et al. 2017).”
Detecting Insider Threat from Behavioral Logs Based on Ensemble and Self-Supervised Learning
Zhang, C., Wang, S., Zhan, D., Yu, T., Wang, T., & Yin, M. (2021) · Security and Communication Networks · doi:10.1155/2021/4148441 · Cited by 30
“(is part will be discussed in Section 3.2 (ii) After obtaining the feature sequence, we use an LSTM-based detector to detect malicious sessions and propose an ensemble strategy to avoid the overfitting problem in the process of training.”
MethodInfluentialSelf-Supervised Random Forest on Transformed Distribution for Anomaly Detection
Liu, J., Wang, H., Hang, H., Ma, S., Shen, X., & Shi, Y. (2025) · IEEE Transactions on Neural Networks and Learning Systems · doi:10.1109/tnnls.2023.3348833 · Cited by 28
“Within the finance sector, anomaly detection plays a crucial role in fraud detection [7], [8], [9], [10], [11], [12].”
Metadata
- Authors
- Ergen, T., & Kozat, S. S.
- Venue
- IEEE Transactions on Neural Networks and Learning Systems
- Published
- 2020-08
- Volume
- 31
- Issue
- 8
- Pages
- 3127-3141
- ISSN
- 2162-237X (ISSN-L)
- 2162-2388
- OpenAlex
- W2766761849
- Cited by
- 386
- References
- 40
- FWCI
- 16.69
- Type
- journal article
- Language
- en
- Open access
- green
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.