Behavioral Based Insider Threat Detection Using Deep Learning
Open accessThe DOI matches its Crossref record; 37 of the 38 references it cites were found in a registry or an index.
Abstract
The most detrimental cyber attacks are usually not originated by malicious outsiders or malware but from trusted insiders. The main advantage insider attackers have over external elements is their ability to bypass security checks and remain undiscovered, this may cause serious damage to the organizational assets.This paper focuses on insider threat detection through behavioral analysis of users. User behavior is categorized as normal or malicious based on user activity. A series of events and activities are analyzed for feature selection to efficiently detect adversarial behavior. Selected feature vectors are used for model training during the implementation phase. A deep learning based approach is proposed that detects insiders with greater accuracy and low false positive rate. A rich event / user role based feature set containing Logon/Logoff events, User_role, Functional_unit etc are used for detection. The dataset used is the CMU CERT synthetic insider threat dataset r4.2. Performance of our proposed algorithm has been compared to other well-known techniques i.e. long short term Memory- convolutional neural network, random forest, long short term memory- recurrent neural network, one class support vector machine , Markov chain model,multi state long short term memory & convolutional neural network, gated recurrent unit & skipgram. The comparison proved that our novel approach produces relatively good accuracy( 90.60%), precision(97%) and F1 Score (94%).
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 cited source doesn’t support the claim as written.
In the citing paper
“Trade-offs involve increased complexity, raising computational demands and reducing explainability compared to traditional ML [28,39].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [28]
Checked by a reasoning model — may be wrong.
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Several studies [45], [49], [55], [57] , [62] have demonstrated that deep learning, characterized by the use of neural networks with multiple layers, has remarkable capabilities in capturing intricate patterns within complex datasets.”
From A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods (2024) · cites this paper as [49]
Experimental — accuracy not yet measuredThe source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Studies justify preprocessing as essential for reducing noise, normalizing data variations, and enhancing model performance, addressing QA1 by providing clear lower metrics [28,39].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [28]
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
A framework for understanding and predicting insider attacks
Schultz, E. E. (2002) · Computers & Security · doi:10.1016/s0167-4048(02)01009-x · Cited by 324
Insider Threat Detection with Deep Neural Network
Yuan, F., Cao, Y., Shang, Y., Liu, Y., Tan, J., & Fang, B. (2018) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-93698-7_4 · Cited by 168 · cited 3×
“A technique using LSTM-CNN algorithm has been shown to identify user anomalous behavior in [5], by monitoring user activities and extracting temporal features.”
MethodInsider Threat Detection Based on User Behavior Modeling and Anomaly Detection Algorithms
Kim, J., Park, M., Kim, H., Cho, S., & Kang, P. (2019) · Applied Sciences · doi:10.3390/app9194018 · Cited by 134
User Behavior Analytics for Anomaly Detection Using LSTM Autoencoder - Insider Threat Detection
Sharma, B., Pokharel, P., & Joshi, B. (2020) · Proceedings of the 11th International Conference on Advances in Information Technology · doi:10.1145/3406601.3406610 · Cited by 130 · cited 1×
“The dataset consists of various csv files [38], in which following are included: 1) logon.csv : Log of users logging in and out on a computer 2) device.csv :Log of users connecting and disconnecting external devices (USB) 3) http.csv :Users browser history 4) email.csv :Email logs 5) file.csv :Log of…”
MethodProactive Insider Threat Detection through Graph Learning and Psychological Context
Brdiczka, O., Liu, J., Price, B., Shen, J., Patil, A., Chow, R., Bart, E., & Ducheneaut, N. (2012) · 2012 IEEE Symposium on Security and Privacy Workshops · doi:10.1109/spw.2012.29 · Cited by 115 · cited 2×
“A framework which uses the combined approach of Structural Anomaly Detection (SA) and Psychological Profiling (PP) of users for insider threat detection is proposed in [36].”
MethodScenario-Based Insider Threat Detection From Cyber Activities
Chattopadhyay, P., Wang, L., & Tan, Y.-P. (2018) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2018.2857473 · Cited by 115 · cited 2×
“A supervised time series based solution using two layer deep auto-encoder can also be used for insider attack detection [4].”
MethodComparing Insider IT Sabotage and Espionage: A Model-Based Analysis
Band, S. R., Cappelli, D. M., Fischer, L. F., et al. (2006) · Figshare · doi:10.1184/r1/6572663.v1 · Cited by 98
Comparing Insider IT Sabotage and Espionage: A Model-Based Analysis
Band, S. R., Cappelli, D. M., Fischer, L. F., Moore, A. P., Shaw, E. D., & Trzeciak, R. F. (2006) · Figshare · doi:10.1184/r1/6572663 · Cited by 98
Anomaly-Based Insider Threat Detection Using Deep Autoencoders
Liu, L., De Vel, O., Chen, C., Zhang, J., & Xiang, Y. (2018) · 2018 IEEE International Conference on Data Mining Workshops (ICDMW) · doi:10.1109/icdmw.2018.00014 · Cited by 79 · cited 1×
“7 [17] Evaluation platform , memory & processing requirement and model train and test time are all missing 8 [24] The performance of the technique is compared with an existing technique Pearson-OCSVM 9 [12] Real life scenario evaluation of the model is missing.”
MethodInsider Threat Detection with Long Short-Term Memory
Lu, J., & Wong, R. K. (2019) · Proceedings of the Australasian Computer Science Week Multiconference · doi:10.1145/3290688.3290692 · Cited by 75 · cited 2×
“The most widely used technique is LSTM [5], [10], [14], [19], [29], [32].”
MethodDeep Learning Based Attribute Classification Insider Threat Detection for Data Security
Meng, F., Lou, F., Fu, Y., & Tian, Z. (2018) · 2018 IEEE Third International Conference on Data Science in Cyberspace (DSC) · doi:10.1109/dsc.2018.00092 · Cited by 74 · cited 3×
“The most widely used technique is LSTM [5], [10], [14], [19], [29], [32].”
BackgroundMethodInfluentialInsider Threat Detection Based on Deep Belief Network Feature Representation
Lin, L., Zhong, S., Jia, C., & Chen, K. (2017) · 2017 International Conference on Green Informatics (ICGI) · doi:10.1109/icgi.2017.37 · Cited by 64 · cited 2×
“Work done in [18] used an unsupervised DBN for unseen feature selection, from multi-domain features obtained from logs.”
MethodAn Integrated Imbalanced Learning and Deep Neural Network Model for Insider Threat Detection
Al-Mhiqani, M. N., Ahmed, R., Zainal, Z., & Isnin, S. N. (2021) · International Journal of Advanced Computer Science and Applications · doi:10.14569/ijacsa.2021.0120166 · Cited by 63
Employee profiling via aspect-based sentiment and network for insider threats detection
Soh, C., Yu, S., Narayanan, A., Duraisamy, S., & Chen, L. (2019) · Expert Systems with Applications · doi:10.1016/j.eswa.2019.05.043 · Cited by 61 · cited 2×
“Aspect based sentiment analysis and social network information of the user using hybrid DL techniques such as Gated Recurrent Unit (GRU) and skipgram are proposed in [30] to detect insider threat.”
MethodDistance Measurement Methods for Improved Insider Threat Detection
Lo, O., Buchanan, W. J., Griffiths, P., & Macfarlane, R. (2018) · Security and Communication Networks · doi:10.1155/2018/5906368 · Cited by 60 · cited 2×
“Work done in [12] uses distance measurement techniques (DL distance, Jaccard Distance and Cosine Distance) through analysis of user activity for insider detection.”
MethodGraph Based Framework for Malicious Insider Threat Detection
Gamachchi, A., Sun, L., & Boztas, S. (2017) · Proceedings of the Annual Hawaii International Conference on System Sciences · doi:10.24251/hicss.2017.319 · Cited by 59
Insider Threat Detection using Deep Autoencoder and Variational Autoencoder Neural Networks
Pantelidis, E., Bendiab, G., Shiaeles, S., & Kolokotronis, N. (2021) · 2021 IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr51186.2021.9527925 · Cited by 55
Insider-threat detection using Gaussian Mixture Models and Sensitivity Profiles
tabash, K. A., & Happa, J. (2018) · Computers & Security · doi:10.1016/j.cose.2018.03.006 · Cited by 51 · cited 2×
“12 [31] Only 15% of the CMU dataset was used for evaluating the model 13 [11] Proposed scheme looks complex and time intensive.”
MethodUser Behavior Profiling using Ensemble Approach for Insider Threat Detection
Singh, M., Mehtre, B. M., & Sangeetha, S. (2019) · 2019 IEEE 5th International Conference on Identity, Security, and Behavior Analysis (ISBA) · doi:10.1109/isba.2019.8778466 · Cited by 44 · cited 4×
“10 [29] X 7 7 7 X X The platform used for evaluation is not mentioned.”
MethodInfluentialA Trust Aware Unsupervised Learning Approach for Insider Threat Detection
Aldairi, M., Karimi, L., & Joshi, J. (2019) · 2019 IEEE 20th International Conference on Information Reuse and Integration for Data Science (IRI) · doi:10.1109/iri.2019.00027 · Cited by 37
Insider Threat Detection Through Attributed Graph Clustering
Gamachchi, A., & Boztas, S. (2017) · 2017 IEEE Trustcom/BigDataSE/ICESS · doi:10.1109/trustcom/bigdatase/icess.2017.227 · Cited by 35 · cited 2×
“Attributed graphs for showing high dimensional, diverse data are used for insider threat detection [35].”
BackgroundMethodRole-based Log Analysis Applying Deep Learning for Insider Threat Detection
Zhang, D., Zheng, Y., Wen, Y., Xu, Y., Wang, J., Yu, Y., & Meng, D. (2018) · Proceedings of the 1st Workshop on Security-Oriented Designs of Computer Architectures and Processors · doi:10.1145/3267494.3267495 · Cited by 35 · cited 1×
“The most widely used technique is LSTM [5], [10], [14], [19], [29], [32].”
MethodAn Insider Threat Detection Method Based on User Behavior Analysis
Jiang, W., Tian, Y., Liu, W., & Liu, W. (2018) · IFIP advances in information and communication technology · doi:10.1007/978-3-030-00828-4_43 · Cited by 26 · cited 1×
“While in [6], detection algorithm XGBoost has been used and behavior characteristic features are extracted from audit logs.”
MethodImplementation of Insider Threat Detection System Using Honeypot Based Sensors and Threat Analytics
Yamin, M. M., Katt, B., Sattar, K., & Ahmad, M. B. (2019) · Lecture notes in networks and systems · doi:10.1007/978-3-030-12385-7_56 · Cited by 24 · cited 2×
“19 [22] N/A Use of honey pot sensor for keeping track of system calls in real time is cost effective.”
BackgroundMethodJiang, J., Chen, J., Choo, K.-K. R., Liu, K., Liu, C., Yu, M., & Mohapatra, P. (2018) · MILCOM 2018 - 2018 IEEE Military Communications Conference (MILCOM) · doi:10.1109/milcom.2018.8599790 · Cited by 22 · cited 2×
“A user sentiment profile has been designed in [9] to give a prediction scheme using user’s network browsing content and emails.”
BackgroundMethodInsider Threat Detection Using Characterizing User Behavior
Wang, X., Tan, Q., Shi, J., Su, S., & Wang, M. (2018) · IEEE International Conference on Data Science in Cyberspace · doi:10.1109/dsc.2018.00077 · Cited by 20 · cited 1×
“In [21], user behavior data has been extracted by examining shell commands flow, keystrokes and mouse functions during GUI interaction.”
MethodAn Internal Threat Detection Model Based on Denoising Autoencoders
Zhang, Z., Wang, S., & Lu, G. (2019) · Smart innovation, systems and technologies · doi:10.1007/978-981-13-9710-3_41 · Cited by 14 · cited 3×
“De-noising auto-encoders has been used for encoding user log file in [24], while anomalous data has been identified using integrated methods like GMM, buck covariance, OCSVM, isolation forest and local outlier factor.”
MethodGargoyle: A Network-based Insider Attack Resilient Framework for Organizations
Shaghaghi, A., Kanhere, S. S., Kâafar, M. A., Bertino, E., & Jha, S. K. (2018) · Conference on Local Computer Networks · doi:10.1109/lcn.2018.8638245 · Cited by 11
A study on Classification of Insider threat using Markov Chain Model
(2018) · KSII Transactions on Internet and Information Systems · doi:10.3837/tiis.2018.04.027 · Cited by 10
An Event Based Detection of Internal Threat to Information System
Li, Z., & Liu, K. (2019) · Advances in intelligent systems and computing · doi:10.1007/978-3-030-31967-0_5 · Cited by 8 · cited 1×
“The model proposed in [23] works by properly designing rules and regulations into complex events and investigating whether employees conduct conforms to the rules and regulations.”
BackgroundUser Profiling in Anomaly Detection of Authorization Logs
Zamanian, Z., Feizollah, A., Anuar, N. B., Kiah, L. M. M., Srikanth, K., & Kumar, S. (2018) · Lecture Notes in Electrical Engineering · doi:10.1007/978-981-13-2622-6_6 · Cited by 7 · cited 2×
“2 [5] Experimental setup, platform used, memory and processing requirements are all missing 3 [8] The evaluation is performed on both CMU-CERT and private datasets NextLabs.”
MethodDiscovering Suspicious Patterns Using a Graph Based Approach.
Velampalli, S., Mookiah, L., & Eberle, W. (2019) · The Florida AI Research Society · Cited by 7
Tan, S.-S., Na, J., & Duraisamy, S. (2019) · DR-NTU (Nanyang Technological University) · doi:10.1633/jistap.2019.7.1.5 · Cited by 7
Learning Correlation Graph and Anomalous Employee Behavior for Insider Threat Detection
Pratibha, Wang, J., Aggarwal, S., Ji, F., & Tay, W. P. (2018) · International Conference on Information Fusion (FUSION) · doi:10.23919/icif.2018.8455358 · Cited by 6 · cited 1×
“Technique proposed in [20] detects the malicious conduct of an employee based not only on its own activities but also on the malicious activities of the employees with same job roles.”
BackgroundNetwork Packet Analysis for Detecting Malicious Insider
Patil, D. N., & Meshram, B. B. (2018) · IEEE International Conference for Convergence in Technology (I2CT) · doi:10.1109/i2ct.2018.8529451 · Cited by 5 · cited 2×
“18 [16] N/A A graph based approach, in which a weight is assigned to each activity.”
BackgroundMethodImproved Detection of User Malicious Behavior through Log Mining based on IHMM
Liu, C., Zhong, Y., & Wang, Y. (2018) · International Conference on Systems and Informatics (ICSAI) · doi:10.1109/icsai.2018.8599422 · Cited by 5 · cited 1×
“Technique proposed in [7] extracted features and fields from user behavior logs for behavior auditing, and then these log files are used to train the Improved Hidden Markov Model (IHMM) for detection of malicious behavior.”
MethodA State Machine System for Insider Threat Detection
Zhang, H., Agrafiotis, I., Erola, A., Creese, S., & Goldsmith, M. H. (2019) · Lecture notes in computer science · doi:10.1007/978-3-030-15465-3_7 · Cited by 3 · cited 2×
“20 [34] Effective with minimal time and memory requirements.”
Background
Research works printed but not linked: 4
- 2016, Insider Threat Test Dataset
- 28. Gaurang Gavai, Kumar Sricharan, Dave Gunning, John Hanley, Mudita Singhal, and Rob Rolleston."Supervised and Unsupervised methods to detect Insider Threat from Enterprise Social and Online Activity Data" Journal of Wireless Mobile Networks, Ubiquitous Computing, and De- pendable Applications, volume: 6
- 2. "Insider threat report 2019"
- 1. "Insider Report 2018", CA Technologies VOLUME 4, 2016
Cited by
Alzaabi, F. R., & Mehmood, A. (2024) · IEEE Access · doi:10.1109/access.2024.3369906 · Cited by 204
“In this context, the effectiveness of the Variational Autoencoder(VAE) is demonstrated in [49] in identifying internal threats with high accuracy.”
BackgroundA Comprehensive Review of AI’s Current Impact and Future Prospects in Cybersecurity
Siam, A. A., Alazab, M., Awajan, A. W., & Faruqui, N. (2025) · IEEE Access · doi:10.1109/access.2025.3528114 · Cited by 88
“As shown in Table 6, RNNs are widely used to detect insider threats through sequential behavior analysis [86], while deep neural networks (DNNs) excel in advanced threat detection by extracting complex patterns from endpoint data [85].”
Wang, Z. Q., & El Saddik, A. (2023) · IEEE Access · doi:10.1109/access.2023.3324371 · Cited by 49
BRITD: behavior rhythm insider threat detection with time awareness and user adaptation
Song, S., Gao, N., Zhang, Y., & Ma, C. (2024) · Cybersecurity · doi:10.1186/s42400-023-00190-9 · Cited by 45
“…et al. 2018), DBN (Lin et al. 2017), CNN (Hu et al. 2019; Bu and Cho 2020), RNN (Zhang et al. 2018; Yuan et al. 2019; Tuor et al. 2017; Nasir et al. 2021; Dr et al. 2022; Villarreal-Vasquez et al. 2023), Transformer (Yuan et al. 2020), isomorphic graph representation learning (Jiang…”
BackgroundMethodInfluentialAghware, F. O., Ojugo, A. A., Adigwe, W., Odiakaose, C. C., Ojei, E. O., Ashioba, N. C., Okpor, M. D., & Geteloma, V. O. (2024) · Journal of Computing Theories and Applications · doi:10.62411/jcta.10323 · Cited by 82
Metadata
- Authors
- Nasir, R., Afzal, M., Latif, R., & Iqbal, W.
- Affiliations
- National University of Sciences and Technology (PK)
- Prince Sultan University (SA)
- Corresponding author
- Iqbal, Waseem
- Venue
- IEEE Access
- Published
- 2021
- Volume
- 9
- Pages
- 143266-143274
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W3202733154
- Semantic Scholar
- 278da2f2e2cf30c3231873fa2d252cb053f40138
- Cited by
- 146
- References
- 38
- Citations by year
- 2026: 42 · 2025: 45 · 2024: 35 · 2023: 19 · 2022: 5
- FWCI
- 6.62
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Licence
- Locations
- IEEE Access (publishedVersion, cc-by-nc-nd)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Artificial Intelligence Data Analytics Lab (AIDA) CCIS, Prince Sultan University, Riyadh, Saudi Arabia
- 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, user behavior analysis, behavioral biometrics, deep learning, false positive reduction
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.