Insider Threat Detection Based on User Behavior Modeling and Anomaly Detection Algorithms
Open accessThe DOI matches its Crossref record; 32 of the 36 references it cites were found in a registry or an index.
Abstract
Insider threats are malicious activities by authorized users, such as theft of intellectual property or security information, fraud, and sabotage. Although the number of insider threats is much lower than external network attacks, insider threats can cause extensive damage. As insiders are very familiar with an organization’s system, it is very difficult to detect their malicious behavior. Traditional insider-threat detection methods focus on rule-based approaches built by domain experts, but they are neither flexible nor robust. In this paper, we propose insider-threat detection methods based on user behavior modeling and anomaly detection algorithms. Based on user log data, we constructed three types of datasets: user’s daily activity summary, e-mail contents topic distribution, and user’s weekly e-mail communication history. Then, we applied four anomaly detection algorithms and their combinations to detect malicious activities. Experimental results indicate that the proposed framework can work well for imbalanced datasets in which there are only a few insider threats and where no domain experts’ knowledge is provided.
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
Figures




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 check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“The dataset defines three key insider threat scenarios: Scenario 1 involves an employee misusing removable media to upload confidential data to wikileaks.orgbefore leaving the company [9] .”
From User Behavior Analytics for Insider Threat using Transformer Based Approach (2026) · cites this paper as [9]
Experimental — accuracy not yet measured
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
(2003) · Journal of Machine Learning Research · doi:10.5555/944919.944937 · Cited by 32,337
Social Network Analysis: Methods and Applications
Wasserman, S., & Faust, K. (1994) · doi:10.1017/cbo9780511815478 · Cited by 17,557
Blei, D. M., Ng, A. Y., & Jordan, M. I. (2002) · Advances in Neural Information Processing Systems 14 · doi:10.7551/mitpress/1120.003.0082 · Cited by 12,223
Chandola, V., Banerjee, A., & Kumar, V. (2009) · ACM Computing Surveys · doi:10.1145/1541880.1541882 · Cited by 11,687 · cited 1×
“Alternatively, in practice, one-class classification algorithms can be used in such unbalanced data environments [29] Gauss [30] assumes that the entire normal user behavior cases are drawn from a single multivariate Gaussian distribution (Figure 4a), as defined in Equation (3): Hence, training Gauss…”
BackgroundWold, S., Esbensen, K., & Geladi, P. (1987) · Chemometrics and Intelligent Laboratory Systems · doi:10.1016/0169-7439(87)80084-9 · Cited by 11,606 · cited 1×
“PCA is a statistical method that finds a new set of axes that preserves the variance of the original dataset as much as possible [34].”
MethodAn introduction to variable and feature selection
GuyonIsabelle, & ElisseeffAndré (2003) · Journal of Machine Learning Research · doi:10.5555/944919.944968 · Cited by 7,715
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×
“[16] employed random forest [17] and isolation forest [18] to classify retirees for the ‘Vegas’ dataset, in which behavior features are extracted from e-mail transmission patterns and contents, logon and logoff records, web browsing patterns, and file access patterns.”
MethodAn Introduction to Variable and Feature Selection.
Guyon, I., & Elisseeff, A. (2003) · Cited by 6,576
Ho, T. K. (2002) · Proceedings of 3rd International Conference on Document Analysis and Recognition · doi:10.1109/icdar.1995.598994 · Cited by 5,054
An introduction to kernel-based learning algorithms
Muller, K.-R., Mika, S., Ratsch, G., Tsuda, K., & Scholkopf, B. (2001) · IEEE Transactions on Neural Networks · doi:10.1109/72.914517 · Cited by 3,473 · cited 1×
“The kernel function (Uniform, Triangular, Gaussian, and Epanechnikov) is a non-negative function that is symmetric about the origin and has an integral value of 1 [33].”
Background
Research works printed but not linked: 9
- Wong, W.-K., Moore, A., Cooper, G., and Wagner, M. (August, January 28). Rule-based anomaly pattern detection for detecting disease. Proceedings of the Eighteenth National Conference on Artificial Intelligence (AAAI-02), Edmonton, AB, Canada.
- Cappelli, D.M., Moore, A.P., and Trzeciak, R.F. (2012). The CERT Guide to Insider Threats: How to Prevent, Detect, and Respond to Information Technology Crimes (Theft, Sabotage, Fraud), Addison-Wesley.
- Lunt, T.F., Jagannathan, R., Lee, R., Whitehurst, A., and Listgarten, S. (1989, January 27–31). Knowledge-based intrusion detection. Proceedings of the Annual AI Systems in Government Conference, Washington, DC, USA.
- Alpaydin, E. (2014). Introduction to Machine Learning, MIT Press.
- Gavai, 2015, Supervised and Unsupervised methods to detect Insider Threat from Enterprise Social and Online Activity Data, JoWUA, 6, 47
- McGough, 2015, Detecting insider threats using Ben-ware: Beneficial intelligent software for identifying anomalous human behavior, J. Wirel. Mob. Netw. Ubiquitous Comput. Dependable Appl., 6, 1
- Ali, 2013, Classification with class imbalance problem, Int. J. Adv. Soft Comput. Appl., 5, 1
- Barnett, V., and Lewis, T. (1994). Outliers in Statistical Data, Wiley.
- Duda, R.O., Hart, P.E., and Stork, D.G. (2012). Pattern Classification, John Wiley & Sons.
Cited by
Items 101–134 of 134
Mensah, F. (2023) · International Journal of Novel Research and Development · doi:10.56975/ijnrd.v8i9.305876 · Cited by 1
Tamirat, M. (2025) · Journal of Electrical Systems · doi:10.52783/jes.7769
“Finally, [16] suggested an insider threat detection based on UBM (user behavior modeling) and anomaly detection algorithms.”
Kumar, M. A. M., Hemanth, M., Ahmed, M. Y., Vardhan, M. T. A., & Vamsi, M. (2025) · Fuzzy Systems and Soft Computing · doi:10.36893/fssc.2025.v20n01.040
Behavioural Analysis in Human-Machine Interaction for Insider Threats
Laczi, S. A., & Póser, V. (2025) · IEEE International Conference on Intelligent Engineering Systems (INES) · doi:10.1109/ines67149.2025.11078220
Rule-Based Learning for Explainable XGBoost Internal Threat Detection
Qiu, Y., Sun, L., Wu, J., Gao, Y., & Yang, J. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-97352-9_28 · Cited by 1
Detecting User Sign-in Anomalies in Cloud-based Logs Using Machine Learning Techniques
AlQahtani, A., & Taher, F. (2025) · International Conference on Communication, Computing, Networking, and Control in Cyber-Physical Systems (CCNCPS) · doi:10.1109/ccncps66785.2025.11135742
“When it comes to the insider threat detection using the user daily activities data set, the Parzen algorithm had the best detection rate of 8 out of 21 cases [1].”
InfluentialBringing Differential Privacy to HPC: Privacy-Preserving Transformations of HPC Traces
Solórzano, A. L. V., Roy, R. B., Schwaller, B., Walton, S. P., Brandt, J. M., & Tiwari, D. (2025) · ACM International Symposium on High-Performance Parallel and Distributed Computing (HPDC) · doi:10.1145/3731545.3731573
Insider Threats and Social Engineering in Healthcare
Olasehan, O. A. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-4918-3.ch002
Cyberpsychology and adversarial thinking for enhanced cybersecurity defenses
Moskwa, F., & Liu, X. M. (2025) · Information and Computer Security · doi:10.1108/ics-08-2024-0186
Vengathattil, S., & Shaffi, S. M. (2025) · Premier journal of science. · doi:10.70389/pjs.100155 · Cited by 2
A Novel Approach for Recognizing and Eliminating Escalation Attack Using AI Techniques
Suman, B., Saikiran, P., Kasim, N., Kakulapati, V., & Kamakshi, M. S. (2025) · Lecture notes in electrical engineering · doi:10.1007/978-981-95-0269-1_164
SlotITD: Insider Threat Detection Method Using Slot-Based Heterogeneous Graph Neural Network
Zhang, C., Qi, Y., Zhu, Y., Jiang, B., Lu, Z., & Guo, T. (2025) · Communications in computer and information science · doi:10.1007/978-981-95-4100-3_34
Chen, Z., & Shi, Y. (2025) · Journal of Circuits Systems and Computers · doi:10.1142/s0218126625504481
Enhancing Behavioral Insider Threat Detection with AI
Bakhit, R. S., Abo‐alian, A., & Badr, N. L. (2025) · International Conference on Intelligent Computing and Information Systems (ICICIS) · doi:10.1109/icicis66182.2025.11313138
“By analyzing user behavior and system data, these models can help organizations identify and mitigate the risks posed by malicious insiders [18].”
Parallel Autoencoder for Unsupervised Anomaly Detection in Large Multimodal User Behavior Data
Gorohov, O., Kazachuk, M., Машечкин, И. В., & Petrovskiy, M. I. (2025) · Lobachevskii Journal of Mathematics · doi:10.1134/s1995080225609087
“Few works [13, 15, 17, 23] have been devoted to analyzing both the context and the content, and no studies have been found related to changes in model performance when content data is added to contextual data.”
InfluentialIbraheem, I. O., Adepoju, T. M., Segbefia, S. K., & Abdulrasaq, A. A. (2025) · Southern African Journal of Security · doi:10.25159/3005-4222/18099
Kumar, V. S., Renu, K., & Rao, C. V. J. (2025) · International Conference on Mobile Networks and Wireless Communications (ICMNWC) · doi:10.1109/icmnwc66779.2025.11354259
AI for Insider Threat Detection and Employee Monitoring
Donthu, S., Sharma, A., Arunarani, A. R., Krishnamoorthy, P., Pandey, V., Sumangala, K., & Bhoopathy, V. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5223-7.ch009
Jayanth, L. K. C. G., Patra, N. K., & Madugula, G. H. N. S. N. R. (2026) · International Journal of Advanced Research in Science Communication and Technology · doi:10.48175/ijarsct-33203
Alakbarov, R. G., Hashimov, M. A., & Alakbarov, O. R. (2026) · International Conference on Expert Clouds and Applications (ICOECA) · doi:10.1109/icoeca68095.2026.11485201
“In the Article [14] highlights weaknesses of rule-based methods for insider threat detection and presents a user behavior modeling and anomaly detection approach.”
Detecting Deviation in User Activity Using Supervised Learning
Miller, C., Bynum, K., & Hinds, C. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-14893-3_23
Supply Chain Risk Management of Insider Threats: A Network-Oriented Computational Analysis
de Jongh, D., de Ridder, Y., Hobbelink, E., Zięcik, N., Bouma, D., Jan Treur, A., & Roelofsma, P. H. M. P. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-16448-3_12
Unsupervised Graph Learning For Insider Threat Detection
Bertrand, S., Germain, P., & Tawbi, N. (2026) · IFIP advances in information and communication technology · doi:10.1007/978-3-032-27993-4_2
Enhancing IoMT Security with Deep Learning In Healthcare Systems
Njie, M. (2026) · International Conference on Intelligent Computing, Networks, and Security (IC-ICNS) · doi:10.1109/ic-icns68863.2026.11537815
“ Signature-Based Systems: The inability to detect new attack methods and the increasing complexity of IoMT systems make these approaches insufficient for comprehensive security in healthcare environments [3], [4].”
Cybersecurity measures and their mitigation
Soni, P., Bhujdhal, T., Shruti, K., Srivastav, S., & Singh, R. (2026) · Elsevier eBooks · doi:10.1016/b978-0-443-30285-5.00007-2
Pahari, A., Adhikari, A., Olukola, O., Sherif, A., & Rahimi, N. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-29003-8_13
BTITD: an insider threat detection method based on behavior-timestamp dual-stream network
ZHANG, C., Yang, G., Tian, T., Jiang, B., Lü, Z., & Guo, T.-W. (2026) · Cybersecurity · doi:10.1186/s42400-026-00591-6 · Cited by 1
“Kim et al. (2019) proposed an insider threat detection framework based on user behavior modeling and anomaly detection algorithms.”
Gaddam, S. V. K., & Mohan, P. R. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-22118-6_28
A session-based insider threat detection approach leveraging the CERT and SPEDIA datasets
Muñoz, A. M., Larriva-Novo, X. A., Sánchez-Zas, C., Álvarez-Campana, M., & Villagrá, V. A. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100946 · Cited by 5
Baruah, J., Coursey, L. E., Mersha, M. A., & Kalita, J. K. (2026) · International Journal of Design Creativity and Innovation · doi:10.1080/21650349.2026.2692941 · Cited by 1
Paul, A., Bashir, S. O., Buhari, M. D., Ngaira, M., & Venkateswarlu, M. (2026) · Discover Artificial Intelligence · doi:10.1007/s44163-026-01753-8
“This distinction cannot be reliably achieved through static rules or purely deterministic models [7, 8].”
Mihaylova, D., & Vassilev, V. (2026) · International Conference on Electronics, Engineering Physics and Earth Science (EEPES) · doi:10.3390/engproc2026154019
A systematic review of federated learning applications in mitigating insider threats
Mdaghri, A. A., Alae, A., & Hilali, A. A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116478
Explainable Transformer Models for Insider Threat Detection in Enterprise Systems
Al-Dhaqm, A., Bamasoud, D. M., Brnawy, R., Bamaqa, A., Alharbi, A. A., & Aljubayri, I. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.21281
“On the modeling side, classical studies applied isolation forests, support vector machines, random forests, and hidden Markov models to aggregated behavioral features [27-29].”
Metadata
- Authors
- Kim, J., Park, M., Kim, H., Cho, S., & Kang, P.
- Affiliations
- Korea University (KR)
- School of Industrial Management Engineering, Korea University, Seoul, Korea
- Corresponding author
- Kang, Pilsung
- Venue
- Applied Sciences
- Publisher
- MDPI AG
- Published
- 2019-09-25
- Volume
- 9
- Issue
- 19
- Pages
- 4018
- ISSN
- 2076-3417 (ISSN-L)
- OpenAlex
- W2976051608
- Cited by
- 134
- References
- 36
- Citations by year
- 2026: 19 · 2025: 30 · 2024: 29 · 2023: 25 · 2022: 15 · 2021: 9 · 2020: 6 · 2019: 1
- FWCI
- 4.24
- Type
- journal article
- Language
- en
- Open access
- gold
- dx.doi.org
- Licence
- Locations
- Applied Sciences (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- National Research Foundation of Korea (NRF-2019R1F1A1060338)
- Korea Electric Power Corporation (R18XA05)
- 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 › Anomaly Detection Techniques and Applications
- Keywords
- insider threat detection, user behavior modeling, anomaly detection, user log data, class imbalance, malicious user behavior
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.