Analyzing Data Granularity Levels for Insider Threat Detection Using Machine Learning
The DOI matches its Crossref record; 53 of the 59 references it cites were found in a registry or an index.
Abstract
Malicious insider attacks represent one of the most damaging threats to networked systems of companies and government agencies. There is a unique set of challenges that come with insider threat detection in terms of hugely unbalanced data, limited ground truth, as well as behaviour drifts and shifts. This work proposes and evaluates a machine learning based system for user-centered insider threat detection. Using machine learning, analysis of data is performed on multiple levels of granularity under realistic conditions for identifying not only malicious behaviours, but also malicious insiders. Detailed analysis of popular insider threat scenarios with different performance measures are presented to facilitate the realistic estimation of system performance. Evaluation results show that the machine learning based detection system can learn from limited ground truth and detect new malicious insiders in unseen data with a high accuracy. Specifically, up to 85% of malicious insiders are detected at only 0.78% false positive rate. The system is also able to quickly detect the malicious behaviours, as low as 14 minutes after the first malicious action. Comprehensive result reporting allows the system to provide valuable insights to analysts in investigating insider threat cases.
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
“Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, designed to handle sequential data, excel in capturing temporal dependencies in user behavior, making them well-suited for insider threat detection [63], [77].”
From A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods (2024) · cites this paper as [77]
In the citing paper
“Challenges include high computational costs, as DL models require significant resources for training on large datasets like Los Alamos cybersecurity events [23,29], limiting real-time deployment [24,31].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [29]
In the citing paper
“Access logs are treated as text sequences, with LSTM recurrent networks yielding 0.72 average AUC-ROC on Los Alamos datasets for anomaly detection [29].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [29]
In the citing paper
“The CERT Insider Threat Dataset, developed by the CERT Coordination Center, is a widely cited resource, containing synthetic logs of user activities, including email, file access, and network interactions, spanning multiple releases (e.g., r4.2, r6.2) [13,29].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [29]
In the citing paper
“The CERT Dataset offers a large volume of data, with millions of log entries across multiple users and scenarios, providing a robust foundation for training ML and DL models like BERT and LSTM, achieving accuracies up to 99% in some studies [25,29].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [29]
1 more claim about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Breiman, L. (2001) · Machine Learning · doi:10.1023/a:1010933404324 · Cited by 133,538 · cited 2×
“These properties have been formally shown to preclude over learning, making the predictions of the RF robust [44].”
BackgroundAdam: A Method for Stochastic Optimization
Kingma, D. P., & Ba, J. (2014) · arXiv · doi:10.48550/arxiv.1412.6980 · Cited by 98,946 · cited 2×
“The resulting combination of per weight learning rate adaption and (stochastic) back-propagation of the error represents a more robust scheme for weight updating than many previous more computationally expensive methods [42].”
BackgroundMethodScikit-learn: Machine Learning in Python
Pedregosa, F., Varoquaux, G., Gramfort, A., Michel, V., Thirion, B., Grisel, O., Blondel, M., Müller, A., Nothman, J., Louppe, G., et al. (2012) · arXiv · doi:10.48550/arxiv.1201.0490 · Cited by 71,016 · cited 1×
“In this research, Python 3.7 is used for data pre-processing steps and Scikit-learn [49] and XGBoost [45] are used for implementing ML algorithms.”
MethodInfluentialXGBoost: A Scalable Tree Boosting System
Chen, T., & Guestrin, C. (2016) · Proceedings of the 22nd ACM SIGKDD International Conference on Knowledge Discovery and Data Mining · doi:10.1145/2939672.2939785 · Cited by 54,569 · cited 2×
“In this research, Python 3.7 is used for data pre-processing steps and Scikit-learn [49] and XGBoost [45] are used for implementing ML algorithms.”
BackgroundMethodInfluentialSMOTE synthetic minority over-sampling technique
Chawla, N. V., Bowyer, K. W., Hall, L. O., & Kegelmeyer, W. P. (2002) · Journal of Artificial Intelligence Research · doi:10.1613/jair.953 · Cited by 32,865 · cited 1×
“Results with random oversampling (increase positive class to 20% of training data) are shown in Table VIII. not shown due to space other oversampling techniques, such as SMOTE [57], and different training settings yield very similar results.”
ResultOn the limited memory BFGS method for large scale optimization
Liu, D. C., & Nocedal, J. (1989) · Mathematical Programming · doi:10.1007/bf01589116 · Cited by 8,560 · cited 1×
“Logistic Regression assumes the lbfgs solver [50] and appeared to perform best under default parameters.”
Method(2011) · Cited by 6,993
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×
“…data to detect unseen malicious insiders, in this section we compare in realistic training condition the performances of employed ML algorithms and Isolation Forest (IF) [53], a prominent unsupervised learning approach that has been employed in many network anomaly detection work recently [54].”
MethodA Survey of Data Mining and Machine Learning Methods for Cyber Security Intrusion Detection
Buczak, A. L., & Guven, E. (2016) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2015.2494502 · Cited by 3,332
Universal approximation bounds for superpositions of a sigmoidal function
Barron, A. R. (1993) · IEEE Transactions on Information Theory · doi:10.1109/18.256500 · Cited by 2,804
Research works printed but not linked: 5
- 2020, Insider Threat Test Dataset
- le, 2019, Machine learning based insider threat modeling and detection, Proc IFIP/IEEE Int Symp Integr Netw Manag, 1
- 2018, Insider Threat 2018 Report
- gavai, 2015, Supervised and unsupervised methods to detect insider threat from enterprise social and online activity data, J Wireless Mobile Netw Ubiquitous Comput Dependable Appl, 6, 47
- 0, Anomaly detection at multiple scales (ADAMS)
Cited by
Alzaabi, F. R., & Mehmood, A. (2024) · IEEE Access · doi:10.1109/access.2024.3369906 · Cited by 204
“Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, designed to handle sequential data, excel in capturing temporal dependencies in user behavior, making them well-suited for insider threat detection [63], [77].”
BackgroundAl-Shehari, T., & Alsowail, R. A. (2021) · Entropy · doi:10.3390/e23101258 · Cited by 193
“In [45], a machine learning based system was proposed to detect insider threats utilizing user-centered analysis.”
MethodA survey on Zero touch network and Service Management (ZSM) for 5G and beyond networks
Liyanage, M., Pham, Q.-V., Dev, K., Bhattacharya, S., Maddikunta, P. K. R., Gadekallu, T. R., & Yenduri, G. (2022) · Journal of Network and Computer Applications · doi:10.1016/j.jnca.2022.103362 · Cited by 151
Anomaly Detection for Insider Threats Using Unsupervised Ensembles
Le, D. C., & Zincir-Heywood, N. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3071928 · Cited by 147
“Furthermore, user-based results are presented in this section in terms of alarms that are raised per user through aggregation of raw (instance-based) anomalous alerts [35], [52].”
BackgroundSelf-citationHashmi, E., Yamin, M. M., & Yayilgan, S. Y. (2024) · AI and Ethics · doi:10.1007/s43681-024-00529-z · Cited by 88
“A similar approach for threat detection was used by Le et al. [70] utilizing the CERT 4 dataset.”
Metadata
- Authors
- Le, D. C., Zincir-Heywood, N., & Heywood, M. I.
- Affiliations
- Dalhousie University (CA)
- Venue
- IEEE Transactions on Network and Service Management
- Published
- 2020-03
- Volume
- 17
- Issue
- 1
- Pages
- 30-44
- ISSN
- 1932-4537 (ISSN-L)
- 2373-7379
- OpenAlex
- W3000429356
- Semantic Scholar
- 7d073697bb52d5da6e01d1b029729ae64c3da3e9
- Cited by
- 191
- References
- 59
- Citations by year
- 2026: 33 · 2025: 44 · 2024: 36 · 2023: 34 · 2022: 16 · 2021: 20 · 2020: 7
- FWCI
- 9.05
- Type
- journal article
- Language
- en
- Open access
- closed
- Licence
- Locations
- IEEE Transactions on Network and Service Management (publishedVersion)
- Funders
- Natural Sciences and Engineering Research Council of Canada
- Topics
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- insider threat detection, data granularity, user behavior analysis, class imbalance, malicious activity detection, false positive rate
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
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Analyzing Data Granularity Levels for Insider Threat Detection Using Machine Learning. https://app.cochat.ai/papers/10.1109/tnsm.2020.2967721
- The paper
- Le, D. C., Zincir-Heywood, N., & Heywood, M. I. (2020). Analyzing Data Granularity Levels for Insider Threat Detection Using Machine Learning. IEEE Transactions on Network and Service Management. https://doi.org/10.1109/tnsm.2020.2967721
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.