Deep Learning-Driven User Legitimacy Prediction Using Keystroke and Mouse Behavioural Dynamics
The DOI matches its Crossref record; 13 of the 14 references it cites were found in a registry or an index.
Abstract
Continuous authentication, based on behavioral dynamics such as keystroke and mouse movement patterns, has emerged as a promising solution to detect insider threats and ensure real-time security in sensitive systems. This paper presents a comprehensive comparison of traditional machine learning methods, including Random Forest (RF), K-Nearest Neighbors (KNN), Logistic Regression (LR), and XGBoost, against deep learning models like Deep Feedforward Neural Networks (DFFNN) and Long Short-Term Memory (LSTM) networks. Both keystroke and mouse dynamics datasets were used to evaluate model performance. The LSTM model consistently outperformed all other approaches, achieving the highest accuracy and precision, particularly on the keystroke dynamics dataset with an accuracy of 88%. Additionally, we highlight the decision time of each model, crucial for real-time authentication systems. Our findings emphasize the advantage of deep learning models in handling sequential data, while traditional models showed slower response times and lower accuracy. The paper concludes with a discussion on the potential for combining both keystroke and mouse dynamics for enhanced continuous authentication.
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
“Subsequent fusion-based research combined keystroke and mouse modalities, demonstrating improved robustness against spoofing and coercion [17].”
From A SIEM-Integrated Cybersecurity Prototype for Insider Threat Anomaly Detection Using Enterprise Logs and Behavioural Biometrics (2025) · cites this paper as [29]
Citations
Cites
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318 · cited 1×
“We evaluate deep learning models like Deep Feedforward Neural Networks (DFFNNs) [6] and LSTM networks [8], alongside classical models such as Random Forest (RF) [9], K-Nearest Neighbors (KNN) [10], Logistic Regression (LR) [11], and XGBoost [12].”
Machine learning: Algorithms, real-world applications and research directions
Sarker, I. H. (2021) · SN Computer Science · doi:10.1007/s42979-021-00592-x · Cited by 5,583 · cited 1×
“Classical models such as Support Vector Machines (SVMs) has been widely used for such tasks, but these methods require manual feature extraction and often struggle to capture the complex, non-linear relationships present in high-dimensional behavioral data [5].”
Ho, T. K. (2002) · Proceedings of 3rd International Conference on Document Analysis and Recognition · doi:10.1109/icdar.1995.598994 · Cited by 5,054
Effective Intrusion Detection System Using XGBoost
Dhaliwal, S. S., Nahid, A.-A., & Abbas, R. (2018) · Information · doi:10.3390/info9070149 · Cited by 503 · cited 1×
“We evaluate deep learning models like Deep Feedforward Neural Networks (DFFNNs) [6] and LSTM networks [8], alongside classical models such as Random Forest (RF) [9], K-Nearest Neighbors (KNN) [10], Logistic Regression (LR) [11], and XGBoost [12].”
Nick, T. G., & Campbell, K. M. (2007) · Methods in Molecular Biology™ · doi:10.1007/978-1-59745-530-5_14 · Cited by 389 · cited 1×
“We evaluate deep learning models like Deep Feedforward Neural Networks (DFFNNs) [6] and LSTM networks [8], alongside classical models such as Random Forest (RF) [9], K-Nearest Neighbors (KNN) [10], Logistic Regression (LR) [11], and XGBoost [12].”
An Insider Threat Detection Approach Based on Mouse Dynamics and Deep Learning
Hu, T., Niu, W., Zhang, X., Liu, X., Lu, J., & Liu, Y. (2019) · Security and Communication Networks · doi:10.1155/2019/3898951 · Cited by 83 · cited 2×
“Hu et al. [13] demonstrated deep learning’s ability to capture complex behavioral patterns, while Goodfellow et al. [7] emphasized its suitability for continuous authentication tasks.”
Kiyani, A. T., Lasebae, A., Ali, K., Rehman, M. U., & Haq, B. (2020) · IEEE Access · doi:10.1109/access.2020.3019467 · Cited by 38 · cited 2×
“These techniques rely on unique behavioral patterns to differentiate between legitimate users and potential attackers, providing an additional layer of security [3], [4].”
Martín, A. G., de Diego, I. M., Fernández-Isabel, A., Beltrán, M., & Fernández, R. R. (2022) · Knowledge-Based Systems · doi:10.1016/j.knosys.2022.108544 · Cited by 34
Multi-Model authentication using keystroke dynamics for Smartphones
Cilia, D., & Inguanez, F. (2018) · IEEE International Conference on Consumer Electronics - Berlin (ICCE-Berlin) · doi:10.1109/icce-berlin.2018.8576226 · Cited by 27 · cited 2×
“Consequently, continuous Authentication has emerged as an essential method for detecting unauthorized access by monitoring user behavior over time [2].”
KeyRecs: A keystroke dynamics and typing pattern recognition dataset
Dias, T., Vitorino, J., Maia, E., Sousa, O., & Praça, I. (2023) · Data in Brief · doi:10.1016/j.dib.2023.109509 · Cited by 27 · cited 1×
“2) Keyboard Dataset: For the keyboard dynamics, we used the Keyrecs dataset [16], which was collected from 99 participants.”
Research works printed but not linked: 3
- Business, 2024, 2024 data breach investigations report
- Zell, 1994, Simulation neuronaler netze
- Goodfellow, 2016, Deep Learning
Cited by
Bera, B., Nandi, S., & Sikdar, B. (2025) · IEEE Transactions on Network Science and Engineering · doi:10.1109/tnse.2025.3643954 · Cited by 6
Mohamed, M. S. M., & Arabo, A. (2025) · doi:10.20944/preprints202511.1003.v1 · Cited by 3
“Subsequent fusion-based research combined keystroke and mouse modalities, demonstrating improved robustness against spoofing and coercion [29].”
Fine-grained continuous user authentication via mouse grip pressure biometrics
Zou, X., Wang, J., Liu, Y., Wu, J., & Liu, G. (2026) · Frontiers in Computer Science · doi:10.3389/fcomp.2026.1867907
Sasikumar, K., & Nagarajan, S. (2026) · Frontiers in Artificial Intelligence · doi:10.3389/frai.2026.1914353
Continuous authentication system based on background analysis of behavioral biometrics
Білоус, В. М., & Dziubenko, K. R. (2026) · Repository of Vinnytsia National Technical University (Vinnytsia National Technical University)
Metadata
- Authors
- AbouRida, O., Nashaat, M., & Gamal El-din Saad, N.
- Affiliations
- Nile University (EG)
- Nile University,Cairo,Egypt
- Venue
- 2024 International Conference on Computer and Applications (ICCA)
- Publisher
- IEEE
- Published
- 2024-12-17
- Pages
- 1-6
- OpenAlex
- W4408862247
- Cited by
- 4
- References
- 14
- Citations by year
- 2026: 3 · 2025: 1
- FWCI
- 1.52
- Type
- conference paper
- Language
- en
- Open access
- closed
- Locations
- International Conference on Computer and Applications (ICCA) (publishedVersion)
- Topics
- Physical Sciences › Computer Science › Information Systems › User Authentication and Security Systems
- Physical Sciences › Computer Science › Signal Processing › Biometric Identification and Security
- Physical Sciences › Computer Science › Computer Networks and Communications › Advanced Authentication Protocols Security
- Keywords
- continuous authentication, keystroke dynamics, insider threat detection, LSTM, deep feedforward neural network, real-time authentication
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: Deep Learning-Driven User Legitimacy Prediction Using Keystroke and Mouse Behavioural Dynamics. https://app.cochat.ai/papers/10.1109/icca62237.2024.10928042
- The paper
- AbouRida, O., Nashaat, M., & Gamal El-din Saad, N. (2024). Deep Learning-Driven User Legitimacy Prediction Using Keystroke and Mouse Behavioural Dynamics. 2024 International Conference on Computer and Applications (ICCA). https://doi.org/10.1109/icca62237.2024.10928042
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.