A New Take on Detecting Insider Threats: Exploring the Use of Hidden Markov Models
The DOI matches its Crossref record; 17 of the 17 references it cites were found in a registry or an index.
Abstract
The threat that malicious insiders pose towards organisations is a significant problem. In this paper, we investigate the task of detecting such insiders through a novel method of modelling a user's normal behaviour in order to detect anomalies in that behaviour which may be indicative of an attack. Specifically, we make use of Hidden Markov Models to learn what constitutes normal behaviour, and then use them to detect significant deviations from that behaviour. Our results show that this approach is indeed successful at detecting insider threats, and in particular is able to accurately learn a user's behaviour. These initial tests improve on existing research and may provide a useful approach in addressing this part of the insider-threat challenge.
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
“HMMs are justified in studies for their ability to capture temporal anomalies in user access patterns, such as irregular login times or excessive data downloads, which deviate from normal profiles [6,11].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [6]
In the citing paper
“For example, Rashid et al. utilized HMMs to detect insider threats by analyzing deviations in user behavior, reporting effective identification of dynamic threats [6].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [6]
In the citing paper
“However, integration with incident reports remains a gap, as noted in ontology-based studies [6,20].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [6]
In the citing paper
“Comparing 4.1 and 4.2, the latter's increased malicious activity (7% vs. lower rates in 4.1) and expanded feature set make it more suitable for dense threat detection, as evidenced by higher accuracy in recent models [6,7].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [6]
In the citing paper
“The manuscript notes limited exploration of incident report analysis (e.g., NIST APEX '07 [15]) for threat modeling [6], with studies like Paxton-Fear et al. [6] suggesting its potential but lacking integration with other data sources.”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [6]
3 more claims about this paper
Create a free account to see every claim other papers make about this one.
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 4×
“However, a LSTM could require significantly more training data in order to be effective; as with all techniques there are pros and cons.”
MethodInfluentialA tutorial on hidden Markov models and selected applications in speech recognition
Rabiner, L. R. (1989) · Proceedings of the IEEE · doi:10.1109/5.18626 · Cited by 22,743 · cited 2×
“As insider threats have become more prevalent, there have been numerous advances in both industry and research towards attack prevention and detection.”
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 1×
“One of the major tools used in exploring insider threat by CERT is System Dynamics diagrams, which aid in defining relationships between different precursors and factors indicative of an attack.”
MethodForney, G. D. (1973) · Proceedings of the IEEE · doi:10.1109/proc.1973.9030 · Cited by 5,647
Detecting intrusions using system calls: alternative data models
Warrender, C., Forrest, S., & Pearlmutter, B. (2003) · Proceedings of the 1999 IEEE Symposium on Security and Privacy (Cat. No.99CB36344) · doi:10.1109/secpri.1999.766910 · Cited by 1,106 · cited 1×
“Keywords Insider threat; Anomaly detection system; Machine learning”
BackgroundUse of K-Nearest Neighbor classifier for intrusion detection
Liao, Y., & Vemuri, V. R. (2002) · Computers & Security · doi:10.1016/s0167-4048(02)00514-x · Cited by 802
Understanding Insider Threat: A Framework for Characterising Attacks
Nurse, J. R. C., Buckley, O., Legg, P. A., Goldsmith, M., Creese, S., Wright, G. R. T., & Whitty, M. (2014) · 2014 IEEE Security and Privacy Workshops · doi:10.1109/spw.2014.38 · Cited by 212 · cited 1×
“Keywords Insider threat; Anomaly detection system; Machine learning”
BackgroundSelf-citationCappelli, D. M., Moore, A. P., & Trzeciak, R. F. (2012) · International Linear Collider · Cited by 192
A Revealing Introduction to Hidden Markov Models
Stamp, M. (2017) · Introduction to Machine Learning with Applications in Information Security · doi:10.1201/9781315213262-2 · Cited by 184 · cited 3×
“[17] M. Stamp.”
MethodInfluentialA novel technique for long-term anomaly detection in the cloud
Vallis, O., Hochenbaum, J., & Kejariwal, A. (2014) · IEEE International Conference on Cloud Computing Technology and Science · Cited by 167
Research works printed but not linked: 3
- 10.5555/784591.784754 · doi:10.5555/784591.784754
- 10.5555/2696535.2696550 · doi:10.5555/2696535.2696550
- Welch L. R., 2003, Hidden Markov Models and the Baum-Welch Algorithm, IEEE Information Theory Society Newsletter, 53
Cited by
A Distributed Deep Learning System for Web Attack Detection on Edge Devices
Tian, Z., Luo, C., Qiu, J., Du, X., & Guizani, M. (2020) · IEEE Transactions on Industrial Informatics · doi:10.1109/tii.2019.2938778 · Cited by 367
“[6].”
Deep learning for insider threat detection: Review, challenges and opportunities
Yuan, S., & Wu, X. (2021) · Computers & Security · doi:10.1016/j.cose.2021.102221 · Cited by 271
Al-Mhiqani, M. N., Ahmad, R., Zainal Abidin, Z., Yassin, W., Hassan, A., Abdulkareem, K. H., Ali, N. S., & Yunos, Z. (2020) · Applied Sciences · doi:10.3390/app10155208 · Cited by 169
“One such example of the recommendation for selecting features is the use of complex models, such as the LSTM recurrent neural network [96] and gated recurrent unit (GRU), such that a rich representation of user behavior can be learned.”
BackgroundMethodInfluentialAl-Shehari, T., & Alsowail, R. A. (2021) · Entropy · doi:10.3390/e23101258 · Cited by 193
“In other anomaly detection approaches, the sequences of insiders acts are modeled to detect any deviations from such sequences [30,31].”
BackgroundMethodInfluentialAnalyzing Data Granularity Levels for Insider Threat Detection Using Machine Learning
Le, D. C., Zincir-Heywood, N., & Heywood, M. I. (2020) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2020.2967721 · Cited by 191
“Another approach to anomaly detection is to model the sequences of user actions and employ them to detect unusual sequences [18], [19].”
BackgroundMethod
Metadata
- Authors
- Rashid, T., Agrafiotis, I., & Nurse, J. R. C.
- Affiliations
- University of Oxford (GB)
- Venue
- Proceedings of the 8th ACM CCS International Workshop on Managing Insider Security Threats
- Publisher
- ACM
- Published
- 2016-10-28
- Pages
- 47-56
- OpenAlex
- W2538737552
- Cited by
- 152
- References
- 17
- Citations by year
- 2026: 8 · 2025: 9 · 2024: 22 · 2023: 17 · 2022: 16 · 2021: 25 · 2020: 19 · 2019: 19 · 2018: 14 · 2017: 2
- FWCI
- 9.97
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- ACM CCS International Workshop on Managing Insider Security Threats (MIST) (publishedVersion)
- Kent Academic Repository (University of Kent) (acceptedVersion)
- 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 › Information Systems › User Authentication and Security Systems
- Keywords
- insider threat detection, malicious insiders, user behavior modeling, anomaly detection, hidden Markov models
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: A New Take on Detecting Insider Threats: Exploring the Use of Hidden Markov Models. https://app.cochat.ai/papers/10.1145/2995959.2995964
- The paper
- Rashid, T., Agrafiotis, I., & Nurse, J. R. C. (2016). A New Take on Detecting Insider Threats: Exploring the Use of Hidden Markov Models. Proceedings of the 8th ACM CCS International Workshop on Managing Insider Security Threats. https://doi.org/10.1145/2995959.2995964
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.