CNN-LSTM-Based Insider Threat Detection Model
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
With the continuous development of electrical, automation, and artificial intelligence (AI) systems, ensuring the security of system data has become increasingly important. Compared to external threats, insider threats to intelligent systems present greater concealment and potential harm. In this article, an insider threat detection model based on the CNN-LSTM (Convolutional Neural Network-Long Short-Term Memory) algorithm is proposed. The method first extracts key features of user behavior through the CNN layer, followed by user behavior prediction using the LSTM layer. Finally, a fully connected layer performs binary classification to identify whether the behavior constitutes a threat. The experiments are conducted using the CMU-CERT R4.2 public dataset. Results from comparative neural network experiments demonstrate that this model achieves stable accuracy and precision rates exceeding 90%, with excellent performance on the ROC curve.
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
“ML and DL algorithms can learn complex, non-linear patterns in user activity data to enhance detection accuracy [11,12].”
From Application of Machine Learning and Deep Learning Techniques for Enhanced Insider Threat Detection in Cybersecurity: Bibliometric Review (2025) · cites this paper as [12]
In the citing paper
“Additionally, hybrid approaches like CNN-LSTM and Random Forest-XGBoost (Table 3) confirm that combining DL's ability to represent complex patterns with ML's interpretability can help reduce false positives [12,36].”
From Application of Machine Learning and Deep Learning Techniques for Enhanced Insider Threat Detection in Cybersecurity: Bibliometric Review (2025) · cites this paper as [12]
Citations
Cites
Applications of Long Short-Term Memory (LSTM) Networks in Polymeric Sciences: A Review
Malashin, I. P., Тынченко, В. С., Gantimurov, A., Nelyub, V., & Бородулин, А. С. (2024) · Polymers · doi:10.3390/polym16182607 · Cited by 214 · cited 1×
“The LSTM algorithm[14], a variant of the Recurrent Neural Network (RNN) in deep learning, is a special type of recurrent neural network that is well-suited for processing time-series data.”
Alzaabi, F. R., & Mehmood, A. (2024) · IEEE Access · doi:10.1109/access.2024.3369906 · Cited by 204 · cited 1×
“2 dataset [16] was selected to train and test the proposed method.”
A graph empowered insider threat detection framework based on daily activities
Hong, W., Yin, J., You, M., Wang, H., Cao, J., Li, J., Liu, M., & Man, C. (2023) · ISA Transactions · doi:10.1016/j.isatra.2023.06.030 · Cited by 57 · cited 1×
“Hong Wei et al. [9] introduced an integrated feature engineering solution based on daily activity, which utilizes an LSTM autoencoder, a residual hybrid network containing GNN 2025 International Conference on Electrical Automation and Artificial Intelligence (ICEAAI) and CNN components, and an…”
Temporal feature aggregation with attention for insider threat detection from activity logs
Pal, P., Chattopadhyay, P., & Swarnkar, M. (2023) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.119925 · Cited by 52 · cited 1×
“Pal Preetam et al. [8] proposed a method for insider threat detection that combines a stacked LSTM and stacked GRU attention model to improve feature extraction and address data imbalance issues.”
Insider Threat Risk Prediction based on Bayesian Network
Elmrabit, N., Yang, S.-H., Yang, L., & Zhou, H. (2020) · Computers & Security · doi:10.1016/j.cose.2020.101908 · Cited by 46 · cited 1×
“Algorithms such as LSTM, XGBoost [4], Bayesian network [5], tree-based structures [6], and graph-based models [7] have all been used in the field of insider threat detection.”
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 · cited 1×
“Singh Malvika et al. [13] used a hybrid learning method and proposed an improved user behavior-based insider threat detection approach.”
Positioning Your Organization to Respond to Insider Threats
Greitzer, F. L., Purl, J., Leong, Y. M., & Sticha, P. J. (2019) · IEEE Engineering Management Review · doi:10.1109/emr.2019.2914612 · Cited by 35 · cited 1×
“…the primary agents of insider threats are internal personnel or individuals with system access, which generally makes these threats more damaging, difficult to detect, and more diverse in terms of attacker methods [3] Existing security measures are often ineffective against insider threats.”
Contextual feature representation for image-based insider threat classification
Duan, S.-M., Yuan, J.-T., & Wang, B. (2024) · Computers & Security · doi:10.1016/j.cose.2024.103779 · Cited by 17 · cited 1×
“Algorithms such as LSTM, XGBoost [4], Bayesian network [5], tree-based structures [6], and graph-based models [7] have all been used in the field of insider threat detection.”
M-EOS: Modified equilibrium optimization based stacked CNN for insider threat detection
Anju, A., & Krishnamurthy, M. (2024) · Wireless Networks · doi:10.1007/s11276-024-03678-5 · Cited by 17 · cited 1×
“Anju A [11] proposed a stacked Convolutional Neural Network-Attention Bidirectional Gated Recurrent Unit (CNN-Attention-BiGRU) model to detect insider threats, improving classification performance while maintaining low complexity.”
Research works printed but not linked: 7
- 2021, The Impact of Insider Threats on Critical Infrastructure
- 2020, Cybersecurity in the Age of Artificial Intelligence
- Zixuan, 2024, Internal network security threat detection method based on XGBoost algorithm, Journal of Jilin University (Information Science Edition), 42, 366
- Xiaoshuang, 2022, Internal threat detection technology based on autoencoder, Computer Engineering and Design, 43, 2725
- Guanghua, 2022, Internal threat detection model based on LSTM-Attention, Information Network Security, 22, 1
- Yifeng, 2019, Research on internal threat detection method under small sample size[J], Small and Micro Computer Systems, 40, 2330
- Yiqing, 2023, Research on power consumption prediction based on CNN+LSTM hybrid model, Computers & Telecommunications, 65
Cited by
Ofori, H. K., Bell-Dzide, K., Brown-Acquaye, W. L., Lempogo, F., Frimpong, S. O., Agbehadji, I. E., & Millham, R. C. (2025) · Symmetry · doi:10.3390/sym17101704 · Cited by 7
Mohamed, M. S. M., & Arabo, A. (2025) · doi:10.20944/preprints202511.1003.v1 · Cited by 3
Song, S., Chen, Y., Shen, X., Wang, H., Li, J., & Gu, Y. (2025) · China Automation Congress (CAC) · doi:10.1109/cac67268.2025.11487334
ITDF: A Deep Learning Insider Threat Detection Framework Based on Abnormal Logon Behavior
Hajr, L., Alhogail, A. A., Albassam, S. A. A., & Berri, J. (2026) · IEEE Access · doi:10.1109/access.2026.3733166
“In another study, Yang et al. [36] proposed a hybrid model that leverages a CNN to extract features from user behavior, which were then fed into an LSTM network to model temporal sequences and classify users’ actions.”
Metadata
- Authors
- Yang, M., Yi, J., Zhu, H., & Tan, L.
- Affiliations
- Beijing Information Science & Technology University (CN)
- ORCID
- Venue
- 2025 International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
- Publisher
- IEEE
- Published
- 2025-01-10
- Pages
- 985-990
- OpenAlex
- W4409475211
- Semantic Scholar
- 4dec476b9509a36e96176b4e5c8a87170e83a840
- Cited by
- 4
- References
- 9
- Citations by year
- 2026: 2 · 2025: 2
- FWCI
- 4.99
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Electrical Automation and Artificial Intelligence (ICEAAI) (publishedVersion)
- Funders
- National Key R&D Program of China (2024QY1703)
- 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, CNN-LSTM, user behavior prediction
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: CNN-LSTM-Based Insider Threat Detection Model. https://app.cochat.ai/papers/10.1109/iceaai64185.2025.10957184
- The paper
- Yang, M., Yi, J., Zhu, H., & Tan, L. (2025). CNN-LSTM-Based Insider Threat Detection Model. 2025 International Conference on Electrical Automation and Artificial Intelligence (ICEAAI). https://doi.org/10.1109/iceaai64185.2025.10957184
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.