User Behavior Profiling using Ensemble Approach for Insider Threat Detection
The DOI matches its Crossref record; 17 of the 19 references it cites were found in a registry or an index.
Abstract
The greatest threat towards securing the organization and its assets are no longer the attackers attacking beyond the network walls of the organization but the insiders present within the organization with malicious intent. Existing approaches helps to monitor, detect and prevent any malicious activities within an organization's network while ignoring the human behavior impact on security. In this paper we have focused on user behavior profiling approach to monitor and analyze user behavior action sequence to detect insider threats. We present an ensemble hybrid machine learning approach using Multi State Long Short Term Memory (MSLSTM) and Convolution Neural Networks (CNN) based time series anomaly detection to detect the additive outliers in the behavior patterns based on their spatial-temporal behavior features. We find that using Multistate LSTM is better than basic single state LSTM. The proposed method with Multistate LSTM can successfully detect the insider threats providing the AUC of 0.9042 on train data and AUC of 0.9047 on test data when trained with publically available dataset for insider threats.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
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?
In the citing paper
“Moreover, supervised learning methods, such as support vector machines (SVM) and random forests, leverage labeled datasets to train models capable of discriminating between normal and malicious activities [73], [74], [75].”
From A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods (2024) · cites this paper as [73]
In the citing paper
“Singh et al. (2019) [51] explored user behaviour profiling for insider threat detection using an ensemble hybrid ML approach, including MSLSTM and CNN, successfully detecting insider threats with an AUC of 0.9042 on train data and 0.9047 on test data.”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [51]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“[19] and Bontemps et al.”
TensorFlow: A system for large-scale machine learning
Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., Devin, M., Ghemawat, S., Irving, G., Isard, M., et al. (2016) · arXiv (Cornell University) · doi:10.48550/arxiv.1605.08695 · Cited by 11,822
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“[3] in his work has presented an overview of anomaly detection techniques.”
BackgroundRecurrent Neural Network Regularization
Zaremba, W., Sutskever, I., & Vinyals, O. (2014) · arXiv (Cornell University) · doi:10.48550/arxiv.1409.2329 · Cited by 2,123 · cited 2×
“al [17], in which it have been used for language modeling.”
MethodA Comparative Study of Anomaly Detection Schemes in Network Intrusion Detection
Lazarevic, A., Ertoz, L., Kumar, V., Ozgur, A., & Srivastava, J. (2003) · Proceedings of the 2003 SIAM International Conference on Data Mining · doi:10.1137/1.9781611972733.3 · Cited by 865 · cited 2×
“Therefore we compare our results with the following existing approaches [23],[24],[25] for threat detection and obtained the threat detection rate of 85% which is better comparative to the existing approaches reported in the literature.”
MethodResultDeep learning approach for Network Intrusion Detection in Software Defined Networking
Tang, T. A., Mhamdi, L., McLernon, D., Zaidi, S. A. R., & Ghogho, M. (2016) · 2016 International Conference on Wireless Networks and Mobile Communications (WINCOM) · doi:10.1109/wincom.2016.7777224 · Cited by 806 · cited 1×
“[13] in his work have used deep learning for anomaly detection system, but results of testing phase were not up to the mark.”
BackgroundA neural network component for an intrusion detection system
Debar, H., Becker, M., & Siboni, D. (2003) · Proceedings 1992 IEEE Computer Society Symposium on Research in Security and Privacy · doi:10.1109/risp.1992.213257 · Cited by 461
Intrusion Detection with Neural Networks
Ryan, J., Lin, M.-J., & Miikkulainen, R. P. (1997) · Cited by 416
Collective Anomaly Detection Based on Long Short-Term Memory Recurrent Neural Networks
Bontemps, L., Cao, V. L., McDermott, J., & Le-Khac, N.-A. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-48057-2_9 · Cited by 245 · cited 1×
“[20] in their work presents clear view about long short term memory but the main drawback as to choose irrelevant features for modeling user behavior language.”
BackgroundMasquerade detection using truncated command lines
Maxion, R. A., & Townsend, T. N. (2003) · Proceedings International Conference on Dependable Systems and Networks · doi:10.1109/dsn.2002.1028903 · Cited by 221 · cited 2×
“Therefore we compare our results with the following existing approaches [23],[24],[25] for threat detection and obtained the threat detection rate of 85% which is better comparative to the existing approaches reported in the literature.”
MethodResult
Research works printed but not linked: 6
- gavai, 2015, Supervised and Unsupervised methods to detect Insider Threat from Enterprise Social and Online Activity Data, JoWUA, 6 4, 47
- veeramachaneni, 2016, AI2”: training a big data machine to defend, Big Data Security on Cloud (BigDataSecurity) IEEE International Conference on High Performance and Smart Computing (HPSC) and IEEE International Conference on Intelligent Data and Security (IDS) 2016 IEEE 2nd International Conference on
- 0, Convolutional neural network
- oka, 2004, Eigen co-occurrence matrix method for masquerade detection, Publications of the Japan Society for Software Science and Technology
- lindauer, 2014, Insider Threat test data set from CERT v6 0
- 10.1109/dsn.2002.1028903 · DOI · Paper page
Cited by
Alzaabi, F. R., & Mehmood, A. (2024) · IEEE Access · doi:10.1109/access.2024.3369906 · Cited by 204
“Moreover, supervised learning methods, such as support vector machines (SVM) and random forests, leverage labeled datasets to train models capable of discriminating between normal and malicious activities [73], [74], [75].”
MethodBehavioral Based Insider Threat Detection Using Deep Learning
Nasir, R., Afzal, M., Latif, R., & Iqbal, W. (2021) · IEEE Access · doi:10.1109/access.2021.3118297 · Cited by 146
“10 [29] X 7 7 7 X X The platform used for evaluation is not mentioned.”
MethodInfluentialInsider Threat Detection Using Machine Learning Approach
Bin Sarhan, B., & Altwaijry, N. (2022) · Applied Sciences · doi:10.3390/app13010259 · Cited by 111
User Modeling and User Profiling: A Comprehensive SurveyPreprint
Purificato, E., Boratto, L., & Luca, E. W. D. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.09660 · Cited by 112
Automation and Orchestration of Zero Trust Architecture: Potential Solutions and Challenges
Cao, Y., Pokhrel, S. R., Zhu, Y., Doss, R., & Li, G. (2024) · Machine Intelligence Research · doi:10.1007/s11633-023-1456-2 · Cited by 97
“Compared with the [123], [122] used Bi-LSTM for efficient feature extraction and used SVM as a classifier to classify user behaviors into normal and malicious.”
BackgroundMethodInfluentialWang, Z. Q., & El Saddik, A. (2023) · IEEE Access · doi:10.1109/access.2023.3324371 · Cited by 49
“2 dataset include classic machine learning algorithms, such as Isolation Forest and one-class SVM, and deep learning models, such as LSTM-RNN [40], multistate LSTM + CNN [41], Hierarchical LSTMs [25], DeepMIT [42], log2vec, log2vec ++ [43] using graphic embeddings, and DD-GCN [51].”
MethodHandling Insider Threat Through Supervised Machine Learning Techniques
Janjua, F., Masood, A., Abbas, H., & Rashid, I. (2020) · Procedia Computer Science · doi:10.1016/j.procs.2020.10.012 · Cited by 48
A comprehensive investigation of clustering algorithms for User and Entity Behavior Analytics
Artioli, P., Maci, A., & Magrì, A. (2024) · Frontiers in Big Data · doi:10.3389/fdata.2024.1375818 · Cited by 54
User Behaviour based Insider Threat Detection using a Hybrid Learning Approach
Singh, M., Mehtre, B. M., Sangeetha, S., & Govindaraju, V. (2023) · Journal of Ambient Intelligence and Humanized Computing · doi:10.1007/s12652-023-04581-1 · Cited by 45
“(Singh et al. 2019) 68.1 PCA + Tree Structure (Legg et al. 2015) 56.2 Distance Methods + HMM (Lo et al. 2018) 55.9 Proposed 84.4 Fig.”
BackgroundMethodResultInfluentialSelf-citationLe, T. D., Dinh, T. L., & Uwizeyemungu, S. (2024) · Technology in Society · doi:10.1016/j.techsoc.2024.102470 · Cited by 40
Insights into user behavioral-based insider threat detection: systematic review
Kamatchi, K., & Uma, E. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01002-6 · Cited by 47
Al‐Shehari, T., Kadrie, M., Al‐Mhiqani, M. N., Alfakih, T. M., AlSalman, H., Uddin, M., Ullah, S. S., & Dandoush, A. (2024) · Scientific Reports · doi:10.1038/s41598-024-73510-9 · Cited by 41
“User behavior profiling, as described in 25 , is an alternative method for detecting insider threats; it involves observing and investigating user behavior action sequences.”
MethodWei, Y., Chow, K.-P., & Yiu, S.-M. (2021) · Forensic Science International: Digital Investigation · doi:10.1016/j.fsidi.2021.301126 · Cited by 32
“In this paper, we use Bidirectional LSTM (BiLSTM) to automatically learn the abstract features [41-45] among the behavior sequences.”
MethodWang, Z. Q., Wang, H., & Saddik, A. E. (2024) · IEEE Access · doi:10.1109/access.2024.3482988 · Cited by 41
“…we conducted data processing before the experiment such as DistilledTrans [7], LSTM-RNN [57], DeepMIT [58], DD-GCN [36], multistate LSTM + CNN [59], Hierarchical LSTMs [32], simultaneous neural learning [60], unsupervised ensembles [61], log2vec [62], log2vec ++ [62], and peering group…”
MethodRandive, K., Mohan, R., & Sivakrishna, A. M. (2023) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2023.103434 · Cited by 27
User behavior based Insider Threat Detection using a Multi Fuzzy Classifier
Singh, M., Mehtre, B., & Sangeetha, S. (2022) · Multimedia Tools and Applications · doi:10.1007/s11042-022-12173-y · Cited by 29
“Figure 10 shows the obtained results for F-Measure for existing methods [2, 6, 17, 24] which achieves 61.72%, 44.9%, 56.5%, and 68.6% of f-measure, as compared to the proposed method which achieves 83.9% of f-measure.”
BackgroundMethodResultInfluentialSelf-citationUser Behaviour based Insider Threat Detection in Critical Infrastructures
Singh, M., Mehtre, B., & Sangeetha, S. (2021) · 2021 2nd International Conference on Secure Cyber Computing and Communications (ICSCCC) · doi:10.1109/icsccc51823.2021.9478137 · Cited by 21
Self-citationAn insider threat detection method based on improved Test-Time Training model
Tao, X., Liu, J., Yu, Y., Zhang, H., & Huang, Y. (2025) · High-Confidence Computing · doi:10.1016/j.hcc.2024.100283 · Cited by 23
Feltus, C. (2022) · International Journal of Systems and Software Security and Protection · doi:10.4018/ijsssp.293236 · Cited by 31
Insider Threat Detection Based on User Behaviour Analysis
Singh, M., Mehtre, B. M., & Sangeetha, S. (2020) · Communications in Computer and Information Science · doi:10.1007/978-981-15-6318-8_45 · Cited by 18
Self-citationRole-based lateral movement detection with unsupervised learning
Powell, B. A. (2022) · Intelligent Systems with Applications · doi:10.1016/j.iswa.2022.200106 · Cited by 24
User Behavior Threat Detection Based on Adaptive Sliding Window GAN
Tao, X., Lu, S., Zhao, F., Lan, R., Chen, L., Fu, L., & Jia, R. (2024) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2024.3355698 · Cited by 13
Transparency, Security, and Workplace Training & Awareness in the Age of Generative AIPreprint
Vaishnav, L., Singh, S., & Cornell, K. A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2501.10389 · Cited by 13
Automation and Orchestration of Zero Trust Architecture:Potential Solutions and ChallengesPreprint
Cao, Y., Pokhrel, S. R., Zhu, Y., Doss, R., & Li, G. (2022) · doi:10.36227/techrxiv.21385929 · Cited by 14
A systematic review on insider threat detection using natural language processing
Kundiya, K., & Haribhakta, Y. (2025) · International Journal of Information Security · doi:10.1007/s10207-025-01145-6 · Cited by 9
Research on Behavior-Based Data Leakage Incidents for the Sustainable Growth of an Organization
Kim, J., Kim, J., & Chang, H. (2020) · Sustainability · doi:10.3390/su12156217 · Cited by 8
Designing Security User Profiles via Anomaly Detection for User Authentication
Sulayman, I. I. M. A., & Ouda, A. H. (2020) · International Symposium on Networks, Computers and Communications (ISNCC) · doi:10.1109/isncc49221.2020.9297252 · Cited by 7
“Singh, et al. [12], focused on user behavior profiling approach to monitor and analyze user behavior action sequence to detect insider threats.”
BackgroundAutomation and Orchestration of Zero Trust Architecture:Potential Solutions and ChallengesPreprint
Cao, Y., Pokhrel, S. R., Zhu, Y., Doss, R., & Li, G. (2022) · doi:10.36227/techrxiv.21385929.v1 · Cited by 7
CGBA: A Efficient Insider Attacker Detection Technique in Machine Learning
Nandini, K., Girisha, G. S., & Reddy, S. R. (2024) · International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI) · doi:10.1109/accai61061.2024.10601886 · Cited by 3
A Framework for Insider Threat Detection Using Role-Based Profile Assessment and Threshold
Al-Na’amneh, Q., Aljawarneh, M. M., & Hazaymih, R. (2025) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3693-9919-4.ch006 · Cited by 5
Behavioral Analytics for Continuous Insider Threat Detection in Zero-Trust ArchitecturesPreprint
Sarraf, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.06708 · Cited by 3
“…giving the AUC of 0.9042 and 0.9047 on training and test respectively, which is the successful operation to identify insider threats by using publicly available datasets [14] Hu et al. (2019) paper talk about how easy insider attackers can use intranet systems because of unauthorized access.”
InfluentialSingh, S., & Chattopadhyay, P. (2023) · IEEE India Conference · doi:10.1109/indicon59947.2023.10440886 · Cited by 3
“Existing ensemble-based insider threat detection techniques [18], [25], [30] are mostly unsupervised and focus on detecting anomalies in user behavior.”
BackgroundMachine Learning-Driven Threat Analysis for Enhancing Security in Data Center Networking
Nagumotu, V. T., Kavuluri, H. V. R., Pathani, A. K., Dasari, A., Chilakapati, V. K., & Keshireddy, S. R. (2022) · American International Journal of Computer Science and Technology · doi:10.63282/3117-5481/aijcst-v4i1p107 · Cited by 12
BERT-Based Sentiment Forensics Analysis for Intrusion Detection
Sayyafzadeh, S., Chi, H., Xu, W., & Roy, K. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00235 · Cited by 2
“Traditional methods in intrusion detection system [16] have historically served as the cornerstone of cybersecurity, relying on rule-based system and signature-based detection algorithm [17][18].”
MethodMITD-Net: Markov image-based threat detection network
Algabri, M. N. A., Alhrazi, F., Luis, C. Q., Abdu, A., Gu, Y. H., & Algabri, R. (2025) · Scientific Reports · doi:10.1038/s41598-025-19275-1 · Cited by 1
“as ensemble learning and user behavior analytics, have become essential components of modern cybersecurity architectures, providing powerful tools for the early detection and prevention of insider-related threats 15–17 .”
Application of machine learning methods to counter insider threat to information security
Strizhkov, V. A. (2023) · Вопросы безопасности · doi:10.25136/2409-7543.2023.4.68856 · Cited by 1
Analysis of User Behavior Patterns using Machine Learning Algorithms
Harshitha, Y. J., & Jayarekha, P. (2023) · International Conference on Recent Advances in Science and Engineering Technology (ICRASET) · doi:10.1109/icraset59632.2023.10419986 · Cited by 1
“[5] The researchers propose an innovative ensemble hybrid machine learning strategy to identify additive outliers in behaviour patterns based on their spatial-temporal properties.”
BackgroundGonzales, O., Huang, S., & Yang, K. (2024) · IEEE International Systems Conference (SysCon) · doi:10.1109/syscon61195.2024.10553441 · Cited by 1
“Another approach in [14] proposes a hybrid deep learning architecture that combines Convolutional Neural Network (CNN) and Long-Short Term Memory (LSTM) on user behavior profiling.”
BackgroundDesign and Implementation of Anomaly Detections for User Authentication Framework
Sulayman, I. A. (2019) · Scholarship@Western (Western University)
DLPS baseado em Deep Learning: Nova Abordagem para Detecção de Exfiltração em HDFS
Martins, J. D. C., Weigang, L., Garcia, L. P. F., & Castro, G. A. (2021) · Anais do Brazilian Workshop on Social Network Analysis and Mining (BraSNAM) · doi:10.5753/brasnam.2021.16144
SemUserProfiling: A Hybrid Knowledge Centric Approach for Semantically Driven User Profiling
Ojha, R., & Deepak, G. (2022) · Lecture notes on data engineering and communications technologies · doi:10.1007/978-981-16-8403-6_29
Palsodkar, E. A. P. (2023) · Advances in Nonlinear Variational Inequalities · doi:10.52783/anvi.v27.296
Borodavka, V., & Yesin, V. I. (2025) · Radiotekhnika · doi:10.30837/rt.2025.1.220.02
Detection and Prediction of Insider Threats: A Survay
Qada, S., Almubarak, S., Meleeh, H., Al-Omary, A. Y., & Al-Ammari, J. (2025) · International Conference on Innovation and Intelligence for Informatics, Computing, and Technologies (3ICT) · doi:10.1109/3ict68299.2025.11442097
“[21 ] 3) Prediction Models Predictive models, including statistical and machine learning algorithms, are used to predict malicious insider activities.”
A Deep Learning Fusion Model for Insider Threat Detection in High Risk Infrastructure
Ali, S. M., Alshahrani, H. M., Razzaque, A., Reshan, M. S. A., Yousaf, M., Alqazzaz, A., Arain, Q. A., & Shaikh, A. (2026) · IET Computers & Digital Techniques · doi:10.1049/cdt2/6332765
Arora, S., Meenu, Gangrade, A., Saranya, M. L., Shamila, M., & Shukla, P. K. (2025) · IEEE International Conference on Innovate for Humanitarian: Tech Solutions for Global Challenge (ICIH) · doi:10.1109/icih67754.2025.11608791
“But these models require labelled datasets, which is non-existent in insider threat detection [14].”
Insider Threat Detection Using Encoder Decoder Transformer with Cross Attention for CERT Dataset
Kumar, K. P., Snehitha, M., Nishitha, B., & Geethika, K. (2026) · International Conference on Trends in Quantum Computing and Emerging Business Technologies (TQCEBT) · doi:10.1109/tqcebt67648.2026.11681233
Anomaly-Based Detection of Insider Threats Using Network Traffic Behaviour
Sumayah, K., Ullas, S., & Sreerag, G. (2026) · International Conference on Emerging Technologies in Computing and Communication (ETCC) · doi:10.1109/etcc69750.2026.11681991
Behavior-driven user profiling: A case study on microsoft entra ID sign-in
Mehri, G. H., Zambon, E., & Zannone, N. (2026) · Journal of Computer Security · doi:10.1177/0926227x261496870
Adversarial-Aware Deep Learning Frameworks for Enhanced Network Threat Detection
Allu, S., Kuraku, S., Shrivastava, N., Marri, M., Mohammed, K. M., & Jalagam, R. (2024) · International Journal of Technology Management and Humanities
Supervised Learning-Based Anomaly Detection for Cybersecurity in High-Speed Networks
John, S., Shrivastava, N., Ravula, B. B., Kandukuri, Y., & Marri, S. M. (2022) · International Journal of Emerging Research in Engineering and Technology · doi:10.63282/3050-922x.ijeret-v3i1p118
Design of a hybrid behavioral profiling framework for intelligent cyber risk assessment
Huskova, V. H., Shkolnikov, V. I., Khalyhov, A., & Lysov, B. S. (2026) · Eastern-European Journal of Enterprise Technologies · doi:10.15587/1729-4061.2026.371521
A DBMS-Independent Proxy Architecture for Secure Database Query Interception and Audit Logging
KABİL, A. O., Kamaşak, M. E., Çer, E., & Sari, S. (2026) · doi:10.1145/3839029.3839045
Metadata
- Authors
- Singh, M., Mehtre, B. M., & Sangeetha, S.
- Affiliations
- National Institute of Technology Tiruchirappalli (IN)
- Institute for Development and Research in Banking Technology (IN)
- ORCID
- Singh, Malvika
- Venue
- 2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA)
- Publisher
- IEEE
- Published
- 2019-01
- Pages
- 1-8
- OpenAlex
- W2964493783
- Cited by
- 44
- References
- 19
- Citations by year
- 2026: 4 · 2025: 7 · 2024: 9 · 2023: 8 · 2022: 7 · 2021: 4 · 2020: 4 · 2019: 1
- FWCI
- 3.46
- Type
- conference paper
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE International Conference on Identity, Security and Behavior Analysis (ISBA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Anomaly Detection Techniques and Applications
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Keywords
- insider threat detection, user behavior profiling, convolutional neural networks, time series anomaly detection, spatio-temporal features, additive outliers
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.