The DOI matches its Crossref record; 79 of the 80 references it cites were found in a registry or an index.
A Comprehensive Survey of Explainable Artificial Intelligence Techniques for Malicious Insider Threat Detection
Open accessAbstract
This survey reviews how explainable AI techniques such as SHAP and LIME are being combined with machine learning and deep learning for malicious insider threat detection.
Overview
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
Citations
Cites
Barredo Arrieta, A., Díaz-Rodríguez, N., Del Ser, J., Bennetot, A., Tabik, S., Barbado, A., Garcia, S., Gil-Lopez, S., Molina, D., Benjamins, R., et al. (2020) · Information Fusion · doi:10.1016/j.inffus.2019.12.012 · Cited by 10,423 · cited 1×
“While earlier surveys such as Arrieta et al. [14] provide conceptual taxonomies and foundational definitions of XAI, they lack domain specificity and do not consider the practical challenges of applying XAI in real-world cybersecurity contexts.”
Mahbooba, B., Timilsina, M., Sahal, R., & Serrano, M. (2021) · Complexity · doi:10.1155/2021/6634811 · Cited by 327 · cited 1×
“Mahbooba et al. [17] emphasize that detecting intent is inherently difficult due to the variability and ambiguity of insider behaviors.”
A Survey of Insider Attack Detection Research
Salem, M. B., Hershkop, S., & Stolfo, S. J. (2008) · Advances in Information Security · doi:10.1007/978-0-387-77322-3_5 · Cited by 280 · cited 1×
“Similarly, ITD-focused reviews like Salem et al. [15] and Sanzgiri et al. [16] primarily explore detection techniques without systematically examining the role of interpretability in supporting trust and operational transparency.”
Moustafa, N., Koroniotis, N., Keshk, M., Zomaya, A. Y., & Tari, Z. (2023) · IEEE Communications Surveys & Tutorials · doi:10.1109/comst.2023.3280465 · Cited by 266 · cited 3×
“TreeInterpreter, also highlighted in [80], provides hierarchical explanations for decision trees, making it an effective tool for intuitive visualization.”
Sharma, B., Sharma, L., Lal, C., & Roy, S. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2023.121751 · Cited by 247 · cited 1×
“Sharma et al. [27] similarly examine the role of XAI in DL-based intrusion detection systems in dynamic environments like IoT networks.”
Gaspar, D., Silva, P., & Silva, C. (2024) · IEEE Access · doi:10.1109/access.2024.3368377 · Cited by 234 · cited 3×
“Incontrast, LIME excels in providing quick, instance-specific interpretations, as seen in its integration with MLP models for intrusion detection in [65].”
InfluentialHouda, Z. A. E., Brik, B., & Khoukhi, L. (2022) · IEEE Open Journal of the Communications Society · doi:10.1109/ojcoms.2022.3188750 · Cited by 220 · cited 10×
“In [23], RF was applied to the UNSW-NB15 dataset, achieving high accuracy (0.99 TPR), but the model was primarily trained on past attack patterns.”
InfluentialE-XAI: Evaluating Black-Box Explainable AI Frameworks for Network Intrusion Detection
Arreche, O., Guntur, T. R., Roberts, J. W., & Abdallah, M. (2024) · IEEE Access · doi:10.1109/access.2024.3365140 · Cited by 215 · cited 4×
“As reported in [36], the model achieved near-perfect classification results, with precision, recall, F1-score, and AUC values all reaching 0.99.”
InfluentialAlzaabi, F. R., & Mehmood, A. (2024) · IEEE Access · doi:10.1109/access.2024.3369906 · Cited by 204
Self-citationNwakanma, C. I., Ahakonye, L. A. C., Njoku, J. N., Odirichukwu, J. C., Okolie, S. A., Uzondu, C., Ndubuisi Nweke, C. C., & Kim, D.-S. (2023) · Applied Sciences · doi:10.3390/app13031252 · Cited by 202
Towards A Rigorous Evaluation Of XAI Methods On Time Series
Schlegel, U., Arnout, H., El-Assady, M., Oelke, D., & Keim, D. A. (2019) · 2019 IEEE/CVF International Conference on Computer Vision Workshop (ICCVW) · doi:10.1109/iccvw.2019.00516 · Cited by 187 · cited 1×
“One such example is the foundational XAI architecture outlined by Schlegel et al. [26].”
Adversarial XAI Methods in Cybersecurity
Kuppa, A., & Le‐Khac, N. (2021) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2021.3117075 · Cited by 170 · cited 2×
“Studies like [35] show that models trained on CICIDS2017 and interpreted via XAI techniques can validate whether learned behaviors align with expected indicators, making it useful for validating model transparency in dynamic traffic environments.”
InfluentialInsider 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 1×
“It includes rich behavioral logs such as logon/logoff activities, email usage, file access, HTTP browsing, and removable media interactions, with each user labeled as benign or malicious based on specific scenarios (e.g., data theft, sabotage, or policy violations) [41], [42].”
Anomaly Detection for Insider Threats Using Unsupervised Ensembles
Le, D. C., & Zincir-Heywood, N. (2021) · IEEE Transactions on Network and Service Management · doi:10.1109/tnsm.2021.3071928 · Cited by 147 · cited 2×
“Le and Zincir-Heywood [18] demonstrate that ensemble learning techniques improve model robustness, while Kumar et al. [19] explore the integration of psychometric data to create more comprehensive user behavior profiles.”
Robust Network Intrusion Detection Through Explainable Artificial Intelligence (XAI)
Barnard, P., Marchetti, N., & DaSilva, L. A. (2022) · IEEE Networking Letters · doi:10.1109/lnet.2022.3186589 · Cited by 145 · cited 2×
“In a study by Barnard et al. [50], XGBoost was tested on the NSL-KDD dataset.”
Black Box Attacks on Explainable Artificial Intelligence(XAI) methods in Cyber Security
Kuppa, A., & Le-Khac, N.-A. (2020) · 2020 International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn48605.2020.9206780 · Cited by 123 · cited 1×
“Unlike traditional closed-box models, XAI techniques provide human-understandable insights into how and why models make specific predictions, thereby increasing trust, accountability, and operational transparency–especially important in high-stakes domains like cybersecurity [20].”
Malicious Insider Attack Detection in IoTs Using Data Analytics
Khan, A. Y., Latif, R., Latif, S., Tahir, S., Batool, G., & Saba, T. (2020) · IEEE Access · doi:10.1109/access.2019.2959047 · Cited by 116 · cited 1×
“It includes rich behavioral logs such as logon/logoff activities, email usage, file access, HTTP browsing, and removable media interactions, with each user labeled as benign or malicious based on specific scenarios (e.g., data theft, sabotage, or policy violations) [41], [42].”
A Novel IoT-Based Explainable Deep Learning Framework for Intrusion Detection Systems
Houda, Z. A. E., Brik, B., & Senouci, S. (2022) · IEEE Internet of Things Magazine · doi:10.1109/iotm.005.2200028 · Cited by 112 · cited 7×
“Architecture-specific methods like Grad-CAM and DeepLIFT offer additional advantages: Grad-CAM, as shown in [48], enables visual inspection of CNN feature activations–helpful for sequential or spatial data–while DeepLIFT, applied in [59], provides granular attribution scores for neurons in DNNs.”
InfluentialRobust Botnet DGA Detection: Blending XAI and OSINT for Cyber Threat Intelligence Sharing
Suryotrisongko, H., Musashi, Y., Tsuneda, A., & Sugitani, K. (2022) · IEEE Access · doi:10.1109/access.2022.3162588 · Cited by 110 · cited 5×
“…used with models such as Random Forest and DNNs to provide consistent feature importance rankings across diverse datasets like DNSLog, UNSW-NB15, and CICIDS17 [21], [22], [23], while LIME has facilitated localized instance-level insights in models trained on IoT and behavioral datasets [24], [25].”
InfluentialHooshmand, M. K., Manjaiah, D. H., Alzighaibi, A. R., Hashim, H. A., Atlam, E.-S., & Gad, I. (2024) · Alexandria Engineering Journal · doi:10.1016/j.aej.2024.03.041 · Cited by 94 · cited 2×
“The SKM-XGB model introduced in [37] also achieved consistently high performance, with approximately 0.99 reported across all metrics in two separate test scenarios.”
InfluentialLe, T.-T.-H., Wardhani, R. W., Putranto, D. S. C., Jo, U., & Kim, H. (2023) · IEEE Access · doi:10.1109/access.2023.3336678 · Cited by 86 · cited 8×
“In [24], A combined method utilizing RF, Gradient Boosting (GB), and DT achieved optimal results on the IoTD20 dataset, with accuracy, precision, recall, and F1-score all equal to 1.”
InfluentialKumar, R., Aljuhani, A., Javeed, D., Kumar, P., Islam, S., & Islam, A. K. M. N. (2024) · Future Generation Computer Systems · doi:10.1016/j.future.2024.02.015 · Cited by 78 · cited 1×
“In [77], the SALSTM + BC (Self-Attentive LSTM with Boosted Classifiers) hybrid model was applied to the N-BaIoT dataset and a custom DTs dataset.”
Using Kernel SHAP XAI Method to Optimize the Network Anomaly Detection Model
Roshan, K., & Zafar, A. (2022) · International Conference on Computing for Sustainable Global Development · doi:10.23919/indiacom54597.2022.9763241 · Cited by 75 · cited 1×
“Similarly, the study in [64] implemented an Auto-Encoder on the same dataset, reaching an accuracy of 0.90, precision of 0.93, recall of 0.90, and an F1-score of 0.91.”
InfluentialLi, X., Li, X., Jia, J., Li, L., Yuan, J., Gao, Y., & Yu, S. (2023) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2023.3245413 · Cited by 73 · cited 1×
“Regulatory standards like the GDPR also highlight the need for transparent AI decisions that affect individuals [10].”
Privilege Escalation Attack Detection and Mitigation in Cloud Using Machine Learning
Mehmood, M., Amin, R., Muslam, M. M. A., Xie, J., & Aldabbas, H. (2023) · IEEE Access · doi:10.1109/access.2023.3273895 · Cited by 70 · cited 1×
“…the XAI-ITD domain continues to face several critical challenges: High false positive rates: Many existing ITD systems rely on predefined behavioral indicators such as abnormal login times, unauthorized access to files, or atypical device usage patterns–to flag suspicious activity [11], [12].”
Distance 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 62 · cited 1×
“These methods help identify which user actions contributed most to a model’s decision, thereby supporting both global and local interpretability [43].”
Houda, Z. A. E., Moudoud, H., Brik, B., & Khoukhi, L. (2023) · IEEE Conference on Computer Communications Workshops (INFOCOM WKSHPS) · doi:10.1109/infocomwkshps57453.2023.10225769 · Cited by 61 · cited 10×
“In [9], RuleFit was applied to the FedIoT model, which utilized federated learning to detect insider threats in decentralized IoT environments.”
InfluentialExplaining Deep Learning-Based Traffic Classification Using a Genetic Algorithm
Ahn, S.-Y., Kim, J., Park, S. Y., & Cho, S. (2020) · IEEE Access · doi:10.1109/access.2020.3048348 · Cited by 58 · cited 1×
“In addition, [62] explored a hybrid approach that combined CNNs with a genetic algorithm for feature optimization.”
Blockchain and explainable AI for enhanced decision making in cyber threat detection
Kumar, P., Javeed, D., Kumar, R., & Islam, A. K. M. N. (2024) · Software: Practice and Experience · doi:10.1002/spe.3319 · Cited by 58 · cited 3×
“This dual-layered system not only improves threat detection and compliance but also strengthens trust across the healthcare ecosystem [19].”
Kostopoulos, N., Kalogeras, D., Pantazatos, D., Grammatikou, M., & Maglaris, V. (2023) · IEEE Access · doi:10.1109/access.2023.3286313 · Cited by 36 · cited 1×
“For example, SHAP was applied in [25], [80], and [81] to interpret predictions from models such as XGBoost, MLP, RF, and SVM. SHAP’s ability to provide consistent, instance-level feature importance rankings makes it a preferred choice for high-dimensional datasets like UNSW-NB15 and ICU-IoT-Flock.”
Holder, E. W., & Wang, N. (2021) · Human-Intelligent Systems Integration · doi:10.1007/s42454-020-00021-z · Cited by 35
Anomaly Detection for Scenario-based Insider Activities using CGAN Augmented Data
Gayathri, R. G., Sajjanhar, A., Xiang, Y., & Ma, X. (2021) · IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom53373.2021.00105 · Cited by 33
A federated and explainable approach for insider threat detection in IoT
Amiri-Zarandi, M., Karimipour, H., & Dara, R. A. (2023) · Internet of Things · doi:10.1016/j.iot.2023.100965 · Cited by 33
Creating an Explainable Intrusion Detection System Using Self Organizing Maps
Ables, J., Kirby, T., Anderson, W. S., Mittal, S., Rahimi, S., Banicescu, I., & Seale, M. A. (2022) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci51031.2022.10022255 · Cited by 32 · cited 2×
“In the study [52], the authors describe the application of Self-Organizing Maps (SOMs) for ITD.”
Machine Learning Explainability for Intrusion Detection in the Industrial Internet of Things
Ahakonye, L. A. C., Nwakanma, C. I., Lee, J.-M., & Kim, D.-S. (2024) · IEEE Internet of Things Magazine · doi:10.1109/iotm.001.2300171 · Cited by 32 · cited 1×
“A study conducted in [79] compared DT, RF, DNN, and transformers to evaluate their effectiveness in detecting insider threats.”
An XAI-based adversarial training approach for cyber-threat detection
AL-Essa, M., Andresini, G., Appice, A., & Malerba, D. (2022) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cy55231.2022.9927842 · Cited by 31 · cited 3×
“[38].”
Explainable Artificial Intelligence to Detect Image Spam Using Convolutional Neural Network
Zhang, Z., Damiani, E., Hamadi, H. A., Yeun, C. Y., & Taher, F. (2022) · International Conference on Cyber Resilience (ICCR) · doi:10.1109/iccr56254.2022.9995839 · Cited by 31
PANACEA: a neural model ensemble for cyber-threat detection
AL-Essa, M., Andresini, G., Appice, A., & Malerba, D. (2024) · Machine Learning · doi:10.1007/s10994-023-06470-2 · Cited by 30
DeepTaskAPT: Insider APT detection using Task-tree based Deep Learning
Mamun, M., & Shi, K. (2021) · 2021 IEEE 20th International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom) · doi:10.1109/trustcom53373.2021.00102 · Cited by 29 · cited 1×
“Advanced language models such as RoBERTa provide deeper contextual understanding, but face limitations in scalability and linguistic ambiguity [11], [31].”
When explainability turns into a threat - using xAI to fool a fake news detection method
Kozik, R., Ficco, M., Pawlicka, A., et al. (2023) · Computers & Security · doi:10.1016/j.cose.2023.103599 · Cited by 28 · cited 1×
“In [70], BERT was applied to the MM-Covid19 dataset to analyze insider threats within text communications, achieving accuracy, precision, and recall scores of 0.93, along with an F1-score of 0.92.”
InfluentialSenanayake, J., Kalutarage, H., Petrovski, A., Piras, L., & Al-Kadri, M. O. (2024) · Journal of Information Security and Applications · doi:10.1016/j.jisa.2024.103741 · Cited by 28 · cited 2×
“The FNN + BC (Feedforward Neural Network with Boosted Classifiers) hybrid model presented in [78] was applied to the LVDAndro dataset, achieving an accuracy of 0.96, precision of 0.94, recall of 0.99, and an F1-score of 0.96.”
InfluentialDetection of Insider Threats using Artificial Intelligence and Visualisation
Koutsouvelis, V., Shiaeles, S. N., Ghita, B., & Bendiab, G. (2020) · IEEE International Conference on Network Softwarization (NetSoft) · doi:10.1109/netsoft48620.2020.9165337 · Cited by 26 · cited 3×
“These behaviors are often difficult to detect, as they closely resemble legitimate user activity [7].”
InfluentialAdaptive Intrusion Detection Systems: Class Incremental Learning for IoT Emerging Threats
Cerasuolo, F., Bovenzi, G., Marescalco, C., Cirillo, F., Ciuonzo, D., & Pescapè, A. (2023) · IEEE International Conference on Big Data (BigData) · doi:10.1109/bigdata59044.2023.10386129 · Cited by 26
An Adversarial Approach for Intrusion Detection Using Hybrid Deep Learning Model
Asaduzzaman, M., & Rahman, M. M. (2022) · International Conference on Information Technology Research and Innovation (ICITRI) · doi:10.1109/icitri56423.2022.9970221 · Cited by 25 · cited 3×
“It enables analysis of session-based deviations and user behavior shifts that could indicate insider activity [39].”
InfluentialApplying One-Class Algorithms for Data Stream-Based Insider Threat Detection
Peccatiello, R. B., Gondim, J. J. C., & Garcia, L. P. F. (2023) · IEEE Access · doi:10.1109/access.2023.3293825 · Cited by 25 · cited 2×
“As demonstrated in studies such as [45] and [56], SHAP enables the tracing of influential features in models trained on complex datasets like UNSW-NB15 and IoT telemetry.”
Deceiving Post-Hoc Explainable AI (XAI) Methods in Network Intrusion Detection
Senevirathna, T., Siniarski, B., Liyanage, M., & Wang, S. (2024) · IEEE Consumer Communications and Networking Conference · doi:10.1109/ccnc51664.2024.10454633 · Cited by 25 · cited 3×
“A similar application was presented in [32], where RF was trained on the NSL-KDD and 5GNIDD datasets.”
InfluentialExplainable SCADA-Edge Network Intrusion Detection System: Tree-LIME Approach
Nwakanma, C. I., Ahakonye, L. A. C., Jun, T., Lee, J. M., & Kim, D. (2023) · IEEE International Conference on Communications, Control, and Computing Technologies for Smart Grids (SmartGridComm) · doi:10.1109/smartgridcomm57358.2023.10333968 · Cited by 22 · cited 3×
“In [47], TreeLIME was introduced as a method specifically designed for explaining the predictions of decision tree-based models, such as the Optimal Decision Tree (ODT) applied to the Edge-IIoT dataset.”
InfluentialExplainable Ensemble-Based Detection of Cyber Attacks on Internet of Medical Things
Alani, M. M., Mashatan, A., & Miri, A. (2023) · IEEE Intl Conf on Dependable, Autonomic and Secure Computing, Intl Conf on Pervasive Intelligence and Computing, Intl Conf on Cloud and Big Data Computing, Intl Conf on Cyber Science and Technology Congress (DASC/PiCom/CBDCom/CyberSciTech) · doi:10.1109/dasc/picom/cbdcom/cy59711.2023.10361448 · Cited by 21 · cited 1×
“The work in [54] introduced an ensemble model consisting of RF, DT, Support Vector Machines (SVM), and XGBoost.”
A Machine Learning Framework & Development for Insider Cyber-crime Threats Detection
Yousef, R., Jazzar, M., Eleyan, A., & Bejaoui, T. (2023) · 2023 International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets58706.2023.10215718 · Cited by 20
Detecting and Identifying Insider Threats Based on Advanced Clustering Methods
Ņikiforova, O., Romānovs, A., Zabiniako, V., et al. (2024) · IEEE Access · doi:10.1109/access.2024.3365424 · Cited by 20 · cited 2×
“This lack of transparency reduces trust and hinders effective decision-making by human analysts [13].”
XcARet: XAI based Green Security Architecture for Resilient Open Radio Access Networks in 6G
Porambage, P., Pinola, J., Rumesh, Y., Чен, Т., & Huusko, J. (2023) · Joint European Conference on Networks and Communications & 6G Summit (EuCNC/6G Summit) · doi:10.1109/eucnc/6gsummit58263.2023.10188316 · Cited by 19
Explainable AI-Based Malicious Traffic Detection and Monitoring System in Next-Gen IoT Healthcare
Gürbüz, E., Turgut, Ö., & Kök, İ. (2023) · International Conference on Smart Applications, Communications and Networking (SmartNets) · doi:10.1109/smartnets58706.2023.10215896 · Cited by 19 · cited 10×
“For example, [25] used KNN with high accuracy (0.99) in the ICU-IoT-Flock dataset for ITD.”
InfluentialKalakoti, R., Nõmm, S., & Bahşi, H. (2023) · International Conference on Machine Learning and Applications · doi:10.1109/icmla58977.2023.00088 · Cited by 18 · cited 10×
“For example, the DeepLift approach used in [60] to interpret DNN predictions on the N-BaIoT dataset achieved high performance, but relied on complex visualizations to convey model reasoning.”
InfluentialLeveraging Explainable AI Methods Towards Identifying Classification Issues on IDS Datasets
Lanfer, E., Sylvester, S., Aschenbruck, N., & Atzmueller, M. (2023) · Conference on Local Computer Networks · doi:10.1109/lcn58197.2023.10223401 · Cited by 17 · cited 1×
“Furthermore, in [34], RF achieved outstanding performance in ITD.”
Explainable AI for Intrusion Detection Systems
Ramyavarshini, P., Sriram, G. K., Rajasekaran, U., & Malini, A. (2022) · International Conference on Contemporary Computing and Informatics (IC3I) · doi:10.1109/ic3i56241.2022.10073356 · Cited by 15
Detecting an Insider Threat and Analysis of XGBoost using Hyperparameter tuning
Mamidanna, S. K., Reddy, C. R. K., & Gujju, A. (2022) · 2022 International Conference on Advances in Computing, Communication and Applied Informatics (ACCAI) · doi:10.1109/accai53970.2022.9752509 · Cited by 14 · cited 3×
“[30] emphasizes the importance of these metrics in ensuring that explanations are not only accurate but also practical for cybersecurity analysts.”
InfluentialFalse Positive Identification in Intrusion Detection Using XAI
Lopes, R. D. S., Duarte, J. C., & Goldschmidt, R. (2023) · IEEE Latin America Transactions · doi:10.1109/tla.2023.10172140 · Cited by 14 · cited 2×
“In the study by [51], KNN was used on the LYCOS-IDS2017 dataset.”
The Insider Threat Detection Method of University Website Clusters Based on Machine Learning
Li, Y., & Su, Y. (2023) · 2023 6th International Conference on Artificial Intelligence and Big Data (ICAIBD) · doi:10.1109/icaibd57115.2023.10206282 · Cited by 14 · cited 1×
“Meanwhile, threat actors–particularly malicious insiders–are adopting advanced technologies, including Artificial Intelligence (AI), to develop stealthier and more adaptive attack strategies [8].”
An Explainable Intrusion Detection System for IoT Networks
Fazzolari, M., Ducange, P., & Marcelloni, F. (2023) · IEEE International Conference on Fuzzy Systems (FUZZ-IEEE) · doi:10.1109/fuzz52849.2023.10309785 · Cited by 14 · cited 2×
“Similarly, in [48], a Fuzzy Decision Tree (FuzzyDT) achieved high precision, recall, and F1-scores of 0.99 on the N-BaIoT dataset.”
InfluentialJiyad, Z. M., Maruf, A. A., Haque, M. M., et al. (2024) · International Conference on Power, Control and Computing Technologies (ICPC2T) · doi:10.1109/icpc2t60072.2024.10475035 · Cited by 14 · cited 9×
“…used with models such as Random Forest and DNNs to provide consistent feature importance rankings across diverse datasets like DNSLog, UNSW-NB15, and CICIDS17 [21], [22], [23], while LIME has facilitated localized instance-level insights in models trained on IoT and behavioral datasets [24], [25].”
InfluentialMetaCluster: A Universal Interpretable Classification Framework for Cybersecurity
Ge, W., Cui, Z., Wang, J., Tang, B., & Li, X. (2024) · IEEE Transactions on Information Forensics and Security · doi:10.1109/tifs.2024.3372808 · Cited by 13 · cited 1×
“The MetaCluster framework was evaluated by Ge et al. [49] across multiple datasets to assess its robustness and generalizability in detecting insider threats.”
Prediction and Detection of Insider Threat Detection using Emails: A Comparision
Mittal, A., & Garg, U. (2023) · 2023 Second International Conference on Electrical, Electronics, Information and Communication Technologies (ICEEICT) · doi:10.1109/iceeict56924.2023.10157297 · Cited by 12
Detection, Explanation and Filtering of Cyber Attacks Combining Symbolic and Sub-Symbolic Methods
Himmelhuber, A., Dold, D., Grimm, S., Zillner, S., & Runkler, T. A. (2022) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci51031.2022.10022249 · Cited by 11 · cited 2×
“Additionally, emerging tools such as GNNExplainer for Graph Neural Networks [68] and Dalex for ensemble DL models [76] have further broadened the scope of model interpretability.”
IoT Network Intrusion Detection: An Explainable AI Approach in Cybersecurity
Rani, J. V., Ali, H. A. S., & Jakka, A. (2023) · International Conference on Communication, Computing and Industry 4.0 (C2I4) · doi:10.1109/c2i659362.2023.10430601 · Cited by 11
Dealing with extremly Unbalanced Data and Detecting Insider Threats with Deep Neural Networks
Besnaci, S., Hafidi, M., & Lamia, M. (2023) · International Conference on Advances in Electronics, Control and Communication Systems (ICAECCS) · doi:10.1109/icaeccs56710.2023.10105103 · Cited by 9 · cited 1×
“Privilege misuse may involve an authorized user abusing access rights, while privilege escalation refers to attempts by unauthorized users to obtain elevated access [6].”
Evaluation of Strategic Decision taken by Autonomous Agent using Explainable AI
Prasad, R. R., Robinson, R. R. R., Thomas, C., & Balakrishnan, N. (2021) · doi:10.1109/isea-isap54304.2021.9689715 · Cited by 8 · cited 1×
“Another approach, described in [67], applied a FeedFwd-NN to the KD99 dataset using Testing with Concept Activation Vectors (TCAV) to provide high-level, human-interpretable concepts–facilitating transparency for non-technical stakeholders.”
A Proposed Approach to Analyze Insider Threat Detection Using Emails
Mittal, A., & Garg, U. (2022) · 2022 3rd International Conference on Computation, Automation and Knowledge Management (ICCAKM) · doi:10.1109/iccakm54721.2022.9990361 · Cited by 8 · cited 1×
“However, UEBA systems frequently generate high false-positive rates due to the inherent variability in legitimate user behavior [28].”
Machmeier, S., Hoecker, M., & Heuveline, V. (2023) · IEEE Symposium Series on Computational Intelligence (SSCI) · doi:10.1109/ssci52147.2023.10371980 · Cited by 8 · cited 4×
“Unlike simpler ML models, where decision trees or rule-based outputs can directly support human reasoning, DL models require advanced XAI techniques–such as Grad-CAM [69] and DeepLift [60]– to provide insights into their decision-making processes.”
InfluentialIzuazu, U. U., Kim, D., & Lee, J. M. (2023) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc58733.2023.10392826 · Cited by 8 · cited 3×
“In one instance, SHAP enabled interpretability in a DNN that achieved 0.99 accuracy, 0.99 precision, 0.98 recall, and a 0.99 F1 score [58].”
InfluentialXAI for Securing Cyber Physical Systems
Patil, A. P., Devarakonda, J., Singuru, M., Tilak, S., & Jadon, S. (2023) · International Conference on Secure Cyber Computing and Communications (ICSCCC) · doi:10.1109/icsccc58608.2023.10176832 · Cited by 7
Developing Explainable Intrusion Detection Systems for Internet of Things
Çelik, A. F., Sağlam, B., & Demirci, S. (2023) · doi:10.1109/isctrkiye61151.2023.10336102 · Cited by 7 · cited 3×
“Its clean labeling and relatively small feature space make it ideal for evaluating the output of explainability tools such as SHAP and LIME, which have been used in CNN and DNN contexts to identify which attributes most influence classification outcomes [23], [33], [36].”
InfluentialKrishnaveni, S., Sivamohan, S., Chen, T., & Sathiyanarayanan, M. (2023) · International Conference on Futuristic Technologies (INCOFT) · doi:10.1109/incoft60753.2023.10425412 · Cited by 7 · cited 3×
“A more sophisticated ensemble architecture was presented in [40], where a Bidirectional Optimized GRU-LSTM model was paired with Enhanced Feature Selection Strategies (EFFS).”
Bit-by-Bit: A Quantization-Aware Training Framework with XAI for Robust Metaverse Cybersecurity
Nkoro, E. C., Nwakanma, C. I., Lee, J., & Kim, D.-S. (2024) · International Conference on Artificial Intelligence in Information and Communication (ICAIIC) · doi:10.1109/icaiic60209.2024.10463374 · Cited by 6
LogicGAN–based Data Augmentation Approach to Improve Adversarial Attack DNN Classifiers
Feltus, C. (2021) · International Conference on Computational Science and Computational Intelligence (CSCI) · doi:10.1109/csci54926.2021.00011 · Cited by 4 · cited 1×
“In [61], a DNN was employed on the LogicGAN dataset, accompanied by innovative explanation methods such as explanation matrices, which illustrate the contribution of specific features.”
Szczepański, M., Pawlicki, M., Kozik, R., & Choraś, M. (2022) · IEEE International Conference on Data Science and Advanced Analytics (DSAA) · doi:10.1109/dsaa54385.2022.10032372 · Cited by 3 · cited 1×
“A lightweight approach was proposed in [74], where the Compact-ANN model was evaluated on the IoT-CyberSec dataset.”
Singh, R., & Deorari, R. (2022) · IEEE Mysore Sub Section International Conference (MysuruCon) · doi:10.1109/mysurucon55714.2022.10478498 · Cited by 3
X-HDNN: Explainable Hybrid DNN for Industrial Internet of Things Backdoor Attack Detection
Ahakonye, L. A. C., Nwakanma, C. I., Lee, J. M., & Kim, D. (2023) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc58733.2023.10393379 · Cited by 2
Explainable Adversarial Mitigation Framework for Zero-Trust Cyber Warfare
Nkoro, E. C., Nwakanma, C. I., Lee, J., & Kim, D. (2023) · International Conference on Information and Communication Technology Convergence (ICTC) · doi:10.1109/ictc58733.2023.10392359 · Cited by 1 · cited 2×
“These predictions were explained with 0.94 accuracy and F1 score [66].”
InfluentialEvan, M. R. I., Rahman, M. M., Mehedi, S. T., et al. (2023) · IEEE Asia-Pacific Conference on Computer Science and Data Engineering (CSDE) · doi:10.1109/csde59766.2023.10487669 · Cited by 1 · cited 1×
“Similarly, [55] implemented the SBPO + RF model, attaining 0.99 in all key performance metrics.”
Influential
Research works printed but not linked: 4
- 2025, The Real Costs of Insider Threats: An In-depth Analysis
- Sanzgiri, 2020, Insider threat detection using deep neural networks, J. Inf. Secur. Appl., 55
- 10.1109/lnet.2022.3186589 · DOI · Paper page
- 2016, Insider threat test dataset
Cited by
Transforming Smart Healthcare Systems with AI-Driven Edge Computing for Distributed IoMT Networks
Almufareh, M. F., Humayun, M., & Haseeb, K. (2025) · Bioengineering · doi:10.3390/bioengineering12111232 · Cited by 14
“Medical equipment with IoMT devices interacts through wearable sensors and emerging technologies to sense and process medical records in real-time environments [21,22].”
Nasir, K., Badri, S. K., Alghazzawi, D., et al. (2026) · Scientific Reports · doi:10.1038/s41598-025-32183-8 · Cited by 7
“Alketbi and Mehmood 7 surveyed XAI methods for insider and intrusion detection, stressing the operational importance of interpretability and resource-awareness.”
AI-Integrated Adaptive Pattern Recognition Algorithms for High-Dimensional Data Analysis
Lokesh, A., & Koneti, H. (2026) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate69073.2026.11518920 · Cited by 3
Integrating Human Factors into Insider Threat Detection – A Systematic Review
Pathirana, N., Roberts, R., Kalutarage, H., & McDermott, C. D. (2026) · ACM Computing Surveys · doi:10.1145/3798089 · Cited by 1
Saranya, S., Malligeswari, N., Graf, F. T., et al. (2025) · Scientific Reports · doi:10.1038/s41598-025-19156-7 · Cited by 1
Metadata
- Authors
- Saeed Alketbi, K., & Mehmood, A.
- Affiliations
- College of Engineering, Abu Dhabi University, Abu Dhabi, United Arab Emirates
- Abu Dhabi University (AE)
- Venue
- IEEE Access
- Published
- 2025
- Volume
- 13
- Pages
- 121772-121798
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4412375142
- Cited by
- 41
- References
- 80
- Citations by year
- 2026: 38 · 2025: 3
- FWCI
- 42.98
- Type
- journal article
- Language
- en
- Open access
- gold
- doi.org
- Locations
- IEEE Access (publishedVersion, cc-by)
- DOAJ (DOAJ: Directory of Open Access Journals) (submittedVersion, cc-by-sa)
- Funders
- Abu Dhabi University’s Office of Research and Sponsored Programs (19300961)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Physical Sciences › Computer Science › Artificial Intelligence › Explainable Artificial Intelligence (XAI)
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Keywords
- insider threat detection, explainable AI, interpretability, SHAP, lime, psychometric indicators, class imbalance, heterogeneous data integration, explainability evaluation metrics, privacy-preserving AI, benchmarking framework, cybersecurity
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.