A Review of Recent Advances, Challenges, and Opportunities in Malicious Insider Threat Detection Using Machine Learning Methods
Open accessThe DOI matches its Crossref record; 94 of the 94 references it cites were found in a registry or an index; 11 of the 70 sources its claims cite were checked for support.
Abstract
Insider threat detection has become a paramount concern in modern times where organizations strive to safeguard their sensitive information and critical assets from malicious actions by individuals with privileged access. This survey paper provides a comprehensive overview of insider threat detection, highlighting its significance in the current landscape of cybersecurity.
Overview
CoChat Summary
TL;DR
This is a survey of malicious insider threat detection using machine learning, deep learning, and NLP, with emphasis on recent methods, datasets, metrics, challenges, and future directions. It argues that learning-based approaches are promising but still limited by data scarcity, interpretability, class imbalance, and real-world deployment constraints.
Key findings
- The paper states that insider threats were responsible for 35% of data breaches in the 2023 Verizon DBIR, that malicious insider threats can inflict 20 times greater damage than external actors, and that the average cost is $4.5 million per breach.
- It identifies four major categories of insider threats: malicious, accidental, fraudulent, and privileged vs. non-privileged, and also discusses duration as another categorization dimension.
- The review says machine learning and deep learning methods have shown promise for insider threat detection, especially behavior-based, anomaly-based, and graph-based approaches; it also highlights the growing use of RNNs, LSTMs, CNNs, GNNs, autoencoders, and NLP.
- The paper notes recurring practical issues: false positives, false negatives, class imbalance, need for large labeled datasets, interpretability problems, and adversarial attacks.
Methods
- This is a narrative review/survey paper rather than an empirical study; it synthesizes prior work on insider threat detection.
- It reviews and compares prior studies, datasets, techniques, and metrics, including examples such as CERT, TWOS, RUU, and Sentiment140, and summarizes methods in Tables 1–4.
- The paper’s main analysis is a structured taxonomy covering threat types, detection approaches, data sources/features, learning-based techniques, evaluation metrics, challenges, and future trends.
Limitations
- The paper states that the field is limited by data scarcity, model interpretability, and adversarial attacks, and calls for explainable AI, hybrid models, and more benchmark datasets.
- It also states that many methods depend on large labeled datasets or otherwise struggle with false positives and class imbalance.
- Evident from the text: because this is a survey, it does not report a new experiment or unified benchmark result of its own; instead it compiles and summarizes results from prior studies.
Model-written summary. Check it against the paper before relying on it.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
6 Valid · 6 Not valid · 40 Not checked · 47 Own results and interpretations
The cited sources support only part of this claim — read each source’s verdict below.
In the paper
“Unsupervised learning approaches, including clustering algorithms like K-Means and hierarchical clustering, are adept at grouping similar behavioral patterns and flagging outliers [61], [70], [71], [72] .”
What the sources say
- Not checked — no full text of the sourcecites [61] matched to “An improved feature extraction algorithm for insider threat using hidden Markov model on user behavior detection” (2022) source
- Not checked — no full text of the sourcecites [70] matched to “Positioning Your Organization to Respond to Insider Threats” (2019) source
- Partly supportedcites [71] Noever, 2019, Classifier suites for insider threat detection, arXiv:1901.10948 sourceExperimental — accuracy not yet measured
The Discussion and Conclusions says unsupervised methods can cluster individuals’ network traffic by activity type and may help identify previously unseen threats. It discusses k-nearest neighbors and auto-encoders, not K-Means or hierarchical clustering, and does not demonstrate that those named algorithms flag outliers. (LLM, conf=0.86)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Rule-based detection is effective in identifying known attack patterns or policy violations, offering control over the detection process for customization to specific security requirements [64], [66].”
What the sources say
- Could not verifycites [64] matched to “Detecting Insider Threat from Behavioral Logs Based on Ensemble and Self-Supervised Learning” (2021) sourceExperimental — accuracy not yet measured
The Related Work section describes matching command sequences and using machine-learning methods to detect malicious behavior, but it does not characterize rule-based detection or assess its effectiveness against known attack patterns or policy violations. Searches for rule-based detection, predefined patterns, and policy violations found no passage addressing the attributed claim; page numbers were not available in our copy. (LLM, conf=0.72)
- Could not verifycites [66] matched to “Insider Threat Risk Prediction based on Bayesian Network” (2020) sourceExperimental — accuracy not yet measured
Our indexed copy of Elmrabit et al. (2020) contains only repository/metadata material — the title and author block (unnumbered cover page), the Scopus/RIS and BIBTEX citation records (Abstract, pp. n.), the licence and embargo note (Abstract), and the research-fingerprint/subject-area listing (Abstract). No body text (introduction, related work, or methodology discussion) is retrievable, so nothing in our copy speaks to rule-based detection, known attack patterns, policy violations, or control/customization for security requirements. Searched queries: 'rule-based detection known attack patterns policy violations', 'signature based intrusion detection limitations insider threat customization security requirements', 'introduction insider threat detection methods anomaly based machine learning', 'related work rule based approach known patterns advantages disadvantages' — all returned only the metadata passages. Absence here is not evidence against the claim; the attribution cannot be checked on our copy. (LLM, conf=0.72)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources that could be checked couldn’t confirm or dispute this claim.
In the paper
“Additionally, autoencoders, a form of unsupervised deep learning, have shown promise in reconstructing normal patterns and identifying anomalies [78].”
What the sources say
- Could not verifycites [78] matched to “Malicious Insider Attack Detection in IoTs Using Data Analytics” (2020) sourceExperimental — accuracy not yet measured
The paper’s sensor-extraction section describes detecting deviations from normal activity, but does not discuss autoencoders or reconstructing normal patterns. Searches for autoencoders and reconstruction-based anomaly detection found no passage addressing those methods. (LLM, conf=0.75)
plainstates an association- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
- Could not verify
The cited sources support only part of this claim — read each source’s verdict below.
In the 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.”
What the sources say
- Not checked — no full text of the sourcecites [45] matched to “BS-Net: A Behavior Sequence Network for Insider Threat Detection” (2021) source
- Partly supportedcites [49] matched to “Behavioral Based Insider Threat Detection Using Deep Learning” (2021) sourceExperimental — accuracy not yet measured
The Proposed Scheme and Comparison of Results sections describe an LSTM autoencoder that detects anomalous user behavior and achieves relatively good performance on insider-threat data. This supports deep learning's ability to identify patterns in that setting, but the paper does not establish the broader claim about intricate patterns across complex datasets generally. (LLM, conf=0.82)
- Not checked — no full text of the sourcecites [55] matched to “Anomaly Detection for Insider Threats Using Unsupervised Ensembles” (2021) source
boosted- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
The sources with a verdict support this claim; the rest weren’t checked yet, have no full text we could read, or their verdicts aren’t rated yet.
In the paper
“The authors of [62], [63] show that the effectiveness of these methods hinges on the quality of the baseline behavior models.”
What the sources say
- Not checked — no full text of the sourcecites [62] matched to “Exploring Adversarial Properties of Insider Threat Detection” (2020) source
- Supportedcites [63] matched to “Empirical Detection Techniques of Insider Threat Incidents” (2020) source
The Detection Mechanisms section (page unavailable) says anomaly-based methods define users’ normal activity patterns and flag deviations. The Limitations section (page unavailable) reports that insufficient features caused normal activities to be flagged as outliers, producing many false alarms. Together, these support the paraphrase that the effectiveness of behavior-based detection depends on how well normal behavior is modeled. (LLM, conf=0.84)
plainstates a cause- Asserted: passes — The authors put it forward as true.
- Checkable: passes — It can be checked against evidence.
- Load-bearing: unclear — It is unclear whether the paper’s conclusions depend on it.
- Based: passes — The paper gives a reason why it holds.
16 more claims · 1 with their cited sources checked
Create a free account to see all 99 claims and to verify the 18 references still open.
- It may state two separate claims as one. 36
- Probably not a substantial claim. 64
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 source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Therefore, despite the advances already achieved in LLM security, a significant gap remains to be filled: current models are susceptible to attacks, particularly in cases where they fail to correctly interpret the semantics of interactions [10].”
From Evaluation of NeMo Guardrails as a Firewall for User–LLM Interaction (2026) · cites this paper as [10]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“However, overreliance on domain-specific features limits generalizability, a gap highlighted in reviews of ML methods [19,34].”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [34]
Experimental — accuracy not yet measuredThe check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“Studies rarely justify dataset selection beyond availability [34], and the lack of real-time, multi-source datasets (e.g., integrating social media or chat logs [27]) restricts model robustness.”
From A systematic review on insider threat detection using natural language processing (2025) · cites this paper as [34]
Experimental — accuracy not yet measured
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
Each contradiction between two passages listed here was confirmed by an independent check.
Rated minor: it would not touch a result — a value no result rests on, a p-value that stays on the same side of the significance level, or a conflict that is clerical, resolved elsewhere in the paper, or outside its own findings.
In the paper
“Digital Object Identifier 10.1109/ACCESS.2017.DOI”
§ I. INTRODUCTION
“Citation information: DOI 10.1109/ACCESS.2024.3369906”
Cited works that were retracted
Works this paper cites that were later retracted, from the retraction notices publishers deposit. Major when the notice came out before this paper was published.
A note, not an issue: for example, a cited work that was retracted only after this paper was published, which its authors could not have known.
In the paper
“The deployment of insider threat detection systems in real security environments demands a nuanced approach that considers not only technical aspects but also navigates the intricacies of organizational dynamics and regulatory landscapes [34], [39].”
Cited work 10.1109/mysurucon55714.2022.9972599 · retracted 2024-03-22 · notice 10.1109/mysurucon55714.2022.10478498 · this paper published 2024
Citations
Cites
1 retracted
Singh, R., & Deorari, R. (2022) · IEEE Mysore Sub Section International Conference (MysuruCon) · doi:10.1109/mysurucon55714.2022.9972599 · Cited by 3 · cited 2×
“The deployment of insider threat detection systems in real security environments demands a nuanced approach that considers not only technical aspects but also navigates the intricacies of organizational dynamics and regulatory landscapes [34], [39].”
BackgroundMethodRetractedAl-Shehari, T., & Alsowail, R. A. (2021) · Entropy · doi:10.3390/e23101258 · Cited by 193
Analyzing 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 · cited 1×
“Recurrent Neural Networks (RNNs) and Long Short-Term Memory (LSTM) networks, designed to handle sequential data, excel in capturing temporal dependencies in user behavior, making them well-suited for insider threat detection [63], [77].”
BackgroundAnomaly 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×
“…demonstrating efficacy in detecting subtle deviations indicative of insider threats [48], [50], [51], [76], 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…”
BackgroundMethodBehavioral Based Insider Threat Detection Using Deep Learning
Nasir, R., Afzal, M., Latif, R., & Iqbal, W. (2021) · IEEE Access · doi:10.1109/access.2021.3118297 · Cited by 146 · cited 2×
“In this context, the effectiveness of the Variational Autoencoder(VAE) is demonstrated in [49] in identifying internal threats with high accuracy.”
BackgroundModeling User Search Behavior for Masquerade Detection
Salem, M. B., & Stolfo, S. J. (2011) · Lecture Notes in Computer Science · doi:10.1007/978-3-642-23644-0_10 · Cited by 129 · cited 1×
“Dataset, introduced by Salem and Stolfo [88], comprises host-based events from 34 regular users and includes masquerade sessions conducted by 14 individuals.”
BackgroundMalicious 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×
“Additionally, autoencoders, a form of unsupervised deep learning, have shown promise in reconstructing normal patterns and identifying anomalies [78].”
BackgroundInsider Threat Detection Using Machine Learning Approach
Bin Sarhan, B., & Altwaijry, N. (2022) · Applied Sciences · doi:10.3390/app13010259 · Cited by 111 · cited 3×
“For privacy-sensitive scenarios, federated learning facilitates collaborative learning across decentralized datasets without compromising individual data privacy [4], [8].”
BackgroundInternet of Things Applications: Opportunities and Threats
Rahmani, A. M., Bayramov, S., & Kiani Kalejahi, B. (2022) · Wireless Personal Communications · doi:10.1007/s11277-021-08907-0 · Cited by 110 · cited 1×
“Employees now access organizational resources from various locations and devices, demanding adaptability in detection strategies [9].”
BackgroundA Review of Insider Threat Detection Approaches With IoT Perspective
Kim, A., Oh, J., Ryu, J., & Lee, K. (2020) · IEEE Access · doi:10.1109/access.2020.2990195 · Cited by 93 · cited 1×
“In an enterprise environment, security data often resides in disparate systems such as network logs, endpoint detection and response (EDR) solutions, user behavior analytics (UBA) platforms, and identity and access management (IAM) systems [91].”
Background
Cited by
Items 101–194 of 194
Deep Study on Automated Adversarial Security Equipment to Machine Learning Technique
Anandaram, H., Shreenidhi, K. S., Kiruthigha, R., et al. (2025) · IGI Global eBooks · doi:10.4018/979-8-3693-7758-1.ch005
Balaji, A., Chaitanya, T. S., Bammidi, T. R., Sireesha, K., & Dulam, D. S. P. (2025) · Wiley eBooks · doi:10.1002/9781394305216.ch10
Improvement in Rare Attack Intrusion Detection Rate Using Machine Learning Algorithms
Soomro, A. M., Waleed, A., Bagchi, S., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-3287-9_29
Alamleh, H., Clark, U., & Karabacak, B. (2025) · International Conference on Smart and Sustainable Technologies (SpliTech) · doi:10.23919/splitech65624.2025.11091686
“Furthermore, comprehensive insider threat programs should be implemented, incorporating regular security training, access monitoring, and behavioral analytics to reduce the risk of internal sabotage [26].”
Assessment of Insider Threats in Computer Networks and Mitigation Techniques
Savita, S., Sidhu, A., Ray, M., Sidhu, A., Shalini, R., & Shamini, G. I. (2025) · International Conference on Networks and Cryptology (NETCRYPT) · doi:10.1109/netcrypt65877.2025.11102776
“Regardless of whether the threats are intentional or unintentional, they severely harm an organization by exposing sensitive information, damaging its reputation and causing loss of money [2].”
Mathan, N., Chaudhary, P., Reddy, B., et al. (2025) · doi:10.1109/netcrypt65877.2025.11102328
“It provides strategies for dealing with this risk and offers tips on countering it, knowing full well that insider attacks can cause as much, if not more, and damage than outside attacks [26].”
Abstract Attack Intention Inference Using Low-Rank Gated Arithmetic Interactive Attention
Yang, W., Wang, M., & Wojtczak, D. (2025) · IEEE International Conference on Cyber Security and Resilience (CSR) · doi:10.1109/csr64739.2025.11129983
“While some machine learning models have been developed to address these scenarios [34], their capabilities remain limited as mentioned above.”
Galadima, I. B., Ithnin, N., Wahab, N. H. A., Osman, M. Z., & Gabi, D. (2025) · Research Square · doi:10.21203/rs.3.rs-7396895/v1 · Cited by 2
Rule-Based Learning for Explainable XGBoost Internal Threat Detection
Qiu, Y., Sun, L., Wu, J., Gao, Y., & Yang, J. (2025) · Lecture notes of the Institute for Computer Sciences, Social Informatics and Telecommunications Engineering · doi:10.1007/978-3-031-97352-9_28 · Cited by 1
Building Cyber Resilience: Artificial Intelligence to Predict Threats and Adapt Responses
Rasheed, A., Nasir, H., Hussain, N., et al. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-5535-9_10
FuseAttenX: Leveraging Attention-Enhanced Deep Learning for Business Strategy Optimization
Mahmud, F. U., Rahman, A., Khan, M. A., Bishnu, K. K., Eva, A. A., & Maua, J. (2025) · IEEE International Conference on Computing and Machine Intelligence (ICMI) · doi:10.1109/icmi65310.2025.11141140 · Cited by 2
“However, traditional machine learning (ML) models often struggle to capture the complex relationships inherent in multi-source business data, such as time-series sales records and customer profiles [2], [3].”
Avaliação do NeMo Guardrails como um Firewall para a Interação Usuário-LLM
Alves, M. G. D. D. O., de Castro, J. V. F., Lima, J. P. D. O., de Azambuja, A. J. G., Oliveira, L. B., & Soares, A. D. S. (2025) · Simpósio Brasileiro de Cibersegurança (SBSeg) · doi:10.5753/sbseg.2025.10665
Insider Threat Prediction Using Machine Learning Techniques: A Literature Review
Kumar, A., Patwa, S., & Jangir, S. K. (2025) · Lecture notes in networks and systems · doi:10.1007/978-981-96-6432-0_36
Mewada, A., Ansari, M. A., Ahmad, S., et al. (2025) · IGI Global eBooks · doi:10.4018/979-8-3373-1832-5.ch009
Cyber Coercion Detection Using LLM-Assisted Multimodal Biometric System
Almehmadi, A. (2025) · Applied Sciences · doi:10.3390/app151910658
Role of Embedded Systems in Smart Energy Management: Challenges, Innovations, and Future Trends
Srivastava, S., Satyanarayana, G. S., Dhasmana, A., Rawat, V., Rana, A. S., & Bisht, Y. S. (2025) · Solar Energy and Sustainable Development · doi:10.51646/jsesd.v14istr2e.797 · Cited by 4
Omer, A. A., & Pasha, A. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-00239-6_21
Zhong, Y., & Liu, Y. (2025) · Cluster Computing · doi:10.1007/s10586-025-05768-1
FlowGraphNet: Efficient Malicious Traffic Detection via Graph Construction
Yang, C., Wang, H., Liu, Y., Ding, Y., Liang, H., & Li, Z. (2025) · Lecture notes in computer science · doi:10.1007/978-981-95-3537-8_27
Log File Based Insider Attacks Detection: A Comparative Analysis
Rajvanshi, S., & Deep, G. (2025) · Engineering cyber-physical systems and critical infrastructures · doi:10.1007/978-3-032-06798-2_23
Singhal, S. K., & Sharma, U. (2025) · Lecture notes in networks and systems · doi:10.1007/978-3-032-06677-0_20
Ardiny, H., & Beigzadeh, A. (2025) · Environmental Science and Pollution Research · doi:10.1007/s11356-025-37249-8
“The combination of crowded settings and transit activity means that an unnoticed source can swiftly contaminate environments, amplifying the scope and impact of exposure events (Alzaabi and Mehmood 2024).”
Technical Risk Indicators for the Critical Pathway to Insider Risk
Claycomb, W. R., & Costa, D. L. (2025) · IEEE International Carnahan Conference on Security Technology (ICCST) · doi:10.1109/iccst63435.2025.11293955
“Many papers and articles exist that propose technical methods for monitoring employee behavior on an organization’s information technology systems to detect potential indicators of insider risk, such as [7,8,18,20], however these do not relate specifically to the CPIR.”
Alshaqhaa, A., Hassan, R. B., Qamar, F., & Ibrahim, A. H. (2026) · IEEE Access · doi:10.1109/access.2025.3650186 · Cited by 1
“Recent insider-threat detection research contrasts classical machine-learning pipelines with emerging deep learning and NLP approaches that better capture complex, privilege-driven attack behaviors [49].”
Mannuru, V., Al-Sinayyid, A., Kadiyala, S., Battula, R. R., & kottala, V. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-12930-7_20
1115 AI and Fuzzy Logic for Threat Detection in Healthcare Networks
Dubey, G. P., Bhujade, R. K., Asthana, S., & Arockiam, D. (2025) · De Gruyter eBooks · doi:10.1515/9783112215722-005 · Cited by 1
Shammi, L., Kanchana, R., Chiranth, M., V, & Sadhvi (2025) · IEEE International Conference on Information Technology, Electronics and Intelligent Communication Systems (ICITEICS) · doi:10.1109/iciteics64870.2025.11341420
“This survey examines insider threat detection with traditional machine learning and advanced natural language processing/language model techniques, demonstrating encouraging outcomes on the CMU CERT dataset [4].”
Forensic-Ready Approaches to Insider Threat Mitigation and Human Behavior Analysis
Arora, P., Tripathi, P., & Verma, S. (2026) · IGI Global eBooks · doi:10.4018/979-8-3373-4898-8.ch014
A Hybrid Machine Learning Framework for Insider Threat Detection and Response
S., S. S., Selvaraj, R., Suresh, V., Gugan, I., & Yogesh, D. (2025) · International Conference on Electronics, Communication and Aerospace Technology (ICECA) · doi:10.1109/iceca66444.2025.11383492
“…intent to steal information or disruption of operations, carelessly used by non-malicious users who incidentally inflict security incidents due to careless use of their accounts, and compromised accounts where a non-malicious user gets hold of the account under the sword of stolen credentials [2].”
Research on Insider Threat Detection Methods Based on Convolutional Neural Networks
Peng, J., Chen, Z., & Jiang, S. (2025) · International Conference on Computing, Communication, Perception and Quantum Technology (CCPQT) · doi:10.1109/ccpqt66408.2025.11383425
“This paper innovatively proposes a novel Insider threat detection framework that deeply integrates feature enhancement technology with one-dimensional convolutional neural networks [9].”
Graph Neural Networks for Advanced Persistent Threat Detection
Tumkur, S. D., Pushpa, M. G., Kurra, S. B., et al. (2025) · IEEE International Conference on Cryptography, Informatics, and Cybersecurity (ICoCICs) · doi:10.1109/icocics68032.2025.11384065
“Traditional methods often fail to identify these stages due to the limited availability of labeled attack data and the subtlety of malicious activities [7].”
Time Series Machine Learning Model for Analyzing Growth of Insider Threats Across Global Sectors
Sharma, N., Budda, R. M., Gogineni, V., Gupta, K. P., & Vivek Kumar., M. (2025) · International Conference of Advances in Engineering and Computing Technologies for Sustainable Development (AECTSD) · doi:10.1109/aectsd65988.2025.11410990
“Alzaabi and Mehmood [1] have presented a quantitative research paper on the state of the art in malicious insider threat detection, using machine learning to investigate the impact of the absence of labeled insider data in the detection of malicious attacks, with attention to analyzing the…”
Predictive Modeling of Insider Threats and Corporate Espionage Through Employee Activity Analysis
Srivarshini, R., Suthish., J., & Senthamilarasi, N. (2026) · International Conference on Mobile Computing and Sustainable Informatics (ICMCSI) · doi:10.1109/icmcsi67283.2026.11412695
“Since the dimensionality of behavioral data is high, Principal Component Analysis is utilized to reduce its complexity while preserving the essential patterns of data, which improves [5] the efficiency of computations and allows for better identification of clusters and outliers.”
Zayed, S. M., AlShathri, S. I., & El‐Shafai, W. (2026) · International Journal of Computational Intelligence Systems · doi:10.1007/s44196-026-01178-2
Explainable AI Models for Insider Threat Detection in Smart Healthcare Systems
Telrandhe, A. V., Puri, C., Nishane, D., & Katade, R. (2026) · International Conference on AI-Driven Smart Systems and Ubiquitous Computing (ICAUC) · doi:10.1109/icauc68182.2026.11441146
“Future studies should therefore be on standardizing longitudinal benchmarks to increase transferability [5, 8], Hybrids of time-NLP, such as BERT to increase accuracy by 5-10 percent [9], and human-in-the-loop to increase trust by 20 percent and ethical accountability [4, 13].”
InfluentialA Comprehensive Review of Anomaly Detection Techniques for Insider Threat Identification
Bhoi, B., Jethava, G., & Jethava, S. (2026) · International Conference on AI-Driven Smart Systems and Ubiquitous Computing (ICAUC) · doi:10.1109/icauc68182.2026.11440999
“[14] Explore AI with wear-ables for MITD.”
InfluentialSoanpet, K. K. K., Kumar, R., & Kumar, R. (2025) · International Conference on Recent Trends in Electrical, Electronics and Computing Technologies (ICRTEECT) · doi:10.1109/icrteect67512.2025.11448780
“Conventional anomaly detection techniques struggle to detect such unseen threats due to their reliance on predefined signatures or statistical models [3].”
Gogoi, M., Masood, S. W., Upadhyay, S., Choudhury, N., & Begum, S. A. (2026) · International Journal of Wavelets Multiresolution and Information Processing · doi:10.1142/s0219691326300021 · Cited by 1
BENIGN-AWARE HISTOGRAM GRADIENT BOOSTING FOR MALICIOUS IOT NETWORK TRAFFIC DETECTION
Derahman, M. N., Qin, Z., Abdullah, A., et al. (2026) · Journal of Information System and Technology Management · doi:10.35631/jistm.1142020
AI for Insider Threat Detection and Employee Monitoring
Donthu, S., Sharma, A., Arunarani, A. R., Krishnamoorthy, P., Pandey, V., Sumangala, K., & Bhoopathy, V. (2026) · Advances in computational intelligence and robotics book series · doi:10.4018/979-8-3373-5223-7.ch009
LIME-Enhanced Insider Threat Detection for Distributed Security Systems
Faqihi, R., Nanda, P., Mohanty, M., Alqahtani, S., & Alrashed, B. (2026) · Lecture notes in computer science · doi:10.1007/978-981-95-8408-6_18 · Cited by 1
Khadka, R., Addo, D., Jegede, Y., & Chen, L. (2026) · Springer eBooks · doi:10.1007/978-3-032-19488-6_4
Change-Aware Temporal Alignment on Heterogeneous Graph Snapshots for Insider Threat Detection
Yang, M., Zhou, Y., Wu, D., Pang, G., & Zhu, C. (2026) · IEEE International Conference on Acoustics Speech and Signal Processing · doi:10.1109/icassp55912.2026.11461839
Chhillar, K., Shrivastava, S., Tomar, D. D., & Verma, A. (2026) · International Conference on Advancing Sustainable Solutions through Technologies (ICASST) · doi:10.1109/icasst68917.2026.11484134
“Machine learning algorithms, when trained on extensive enterprise datasets, excel at differentiating between normal and anomalous behaviors, thereby facilitating continuous monitoring and real-time threat identification [12].”
Eswari Petchiammal, G., Abishek Kashyap., S., Karthikeyan, P., Agash Balaji, B., & Harishankar, K. (2026) · International Conference on Expert Clouds and Applications (ICOECA) · doi:10.1109/icoeca68095.2026.11485181
Stochastic Forensics for Insider Threat Detection using Temporal and Behavioral Artifacts
Satya, M., Nandan, P., & Shalinirajan, R. (2026) · International Conference on Expert Clouds and Applications (ICOECA) · doi:10.1109/icoeca68095.2026.11485238
“As pointed out by [13], it is important that the detection accuracy and the rates of false positives be balanced, especially in the enterprise real-time environment.”
Lightweight Supervised Approach for Behavioral Insider Anomaly Detection from SQL Logs
Mahadi, M. H., Abdullah, Y., Ahmed, M. S., Jahan, N., Safwan, M. N., & Chayon, M. H. R. (2025) · International Conference on Computer and Information Technology (ICCIT) · doi:10.1109/iccit68739.2025.11491429
“Behavioral anomaly detection techniques attempt to learn user patterns from metadata such as login time, IP address, or device usage, but these methods often fail to capture the actual semantic intent behind SQL queries [1], [6].”
Akampurira, P., Edozie, E., Sadiq, B. O., & Buhari, M. D. (2026) · F1000Research · doi:10.12688/f1000research.178351.1
Suresh, C., Kumar, G. M., Smitha Vas, P., Sathya, G., Joshua Issac, A., & Keerthana, N. V. (2026) · IGI Global eBooks · doi:10.4018/979-8-2600-1498-1.ch003
Integrating UEBA-Driven Risk Scoring for Adaptive Attribute Based Decryption
Sunny, M. A. S., Ahmed, I., Arman, H. U., & Rahman, M. (2025) · IEEE International Conference on Robotics, Automation, Artificial-Intelligence and Internet-of-Things (RAAICON) · doi:10.1109/raaicon69033.2025.11502528
“…the field of User and Entity Behavior Analytics (UEBA) has advanced significantly, with machine learning (ML) models like XGBoost and LSTMs [8], [9] proving highly effective in identifying subtle deviations from established norms, thereby providing proactive detection of potential insider…”
Dinesh, J., & Sornalakshmi, K. (2026) · International Conference on Innovative Trends in Information Technology (ICITIIT) · doi:10.1109/icitiit68860.2026.11499694
“Special surveillance techniques also have grown quickly, such as crowd analytics [11], pose-based behavior modelling [12], graph-based interaction reasoning [13], thermal sensing [14], and audio-visual fusion [15].”
Aragão, M. V. C., de Figueiredo, F. A. P., & Mafra, S. B. (2026) · International Journal of Intelligent Systems · doi:10.1155/int/9925751
Tomar, D. D., & Chhillar, K. (2025) · doi:10.1109/rcsm67767.2025.11507575
Ren, X. (2026) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aetcse69203.2026.11504380
“Compared with traditional rule-based methods, machine learning models can automatically discover hidden patterns from historical behavioral data and capture nonlinear relationships among high-dimensional features [5].”
Suryaprakash, T., & Rajagopal, S. (2026) · International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication Engineering (RMKMATE) · doi:10.1109/rmkmate69073.2026.11519044
“Recent studies and practitioner analyses indicate that heterogeneous telemetry sources, behavioral drift, and operational constraints contribute to alert fatigue and limit the effectiveness of existing detection systems [3], [4].”
Enhancing IoT Security with Optimized Machine Learning Models for Malicious Traffic Detection
AlSahafi, A. I. (2026) · International Conference on AI Innovations and Industry (ICAIII) · doi:10.1109/icaiii69475.2026.11521091
“By utilizing ML algorithms, researchers and practitioners can develop systems that not only detect known attack vectors but also generalize to previously unseen malicious activities [15].”
A Deep Learning Fusion Model for Insider Threat Detection in High Risk Infrastructure
Ali, S. M., Alshahrani, H. M., Razzaque, A., Reshan, M. S. A., Yousaf, M., Alqazzaz, A., Arain, Q. A., & Shaikh, A. (2026) · IET Computers & Digital Techniques · doi:10.1049/cdt2/6332765
Hamza, Y. A., & Dabagh, N. B. A. (2026) · Communications in computer and information science · doi:10.1007/978-3-032-24239-6_1
A Graph-Based NLP for Threat Detection in Healthcare
Gaur, J., Hazela, B., Tanwar, S., et al. (2026) · doi:10.1109/icisessc68634.2026.11542786
Maraden, Y., Ananda, Z., Nugraha, I. G. D., et al. (2026) · Electronics · doi:10.3390/electronics15112490
Threat Detection Through Honeypot Data
Singh, S., Sharma, P., Parida, J. A., et al. (2026) · doi:10.1109/icass69550.2026.11547795
“As is evident from Fig.5, the anomaly scores are graphed against time, and the scores are highest at 00:00 hours on 23rd November 2022 [12], [18].”
InfluentialXAI-Enhanced Insider Risk Scoring with Adaptive Weighted Ensemble for Medium-Sized Organizations
Abu-Arqoub, M. H., Marie, R. R., & Titinchi, A. A. (2026) · International Conference on Computational Intelligence Approaches and Applications (ICCIAA) · doi:10.1109/icciaa68481.2026.11543714
“The application of machine learning in the analysis conducted by Alzaabi and Mehmood was examined and resulted in the identification of limitations, such as concept drift, imbalanced datasets, and limited ground truth [10].”
Pari, S. N., Varshini, S. S., & Ramesha, M. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-21164-4_42
Rogell, L., Ho-Quang, T., Shahzad, R. K., & Jolak, R. (2026) · Array · doi:10.1016/j.array.2026.101030
Kaichuan, K., Liu, D., Jin, X., & Geng, G. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581710
“Such attacks typically progress slowly and produce weak, temporally sparse signals [1], resulting in long detection delays.”
A session-based insider threat detection approach leveraging the CERT and SPEDIA datasets
Muñoz, A. M., Larriva-Novo, X. A., Sánchez-Zas, C., Álvarez-Campana, M., & Villagrá, V. A. (2026) · Machine Learning with Applications · doi:10.1016/j.mlwa.2026.100946 · Cited by 5
HITD: Hypergraph Representation Learning for Insider Threat Detection
Tian, C., Kong, D., Zhu, Y. C., An, N., Tian, T., Jiang, B., & Lu, Z. (2026) · International Conference on Computer Supported Cooperative Work in Design (CSCWD) · doi:10.1109/cscwd68734.2026.11581565
“Traditional detection methods, like rule-based systems [4], are often ineffective against sophisticated attacks.”
Is a Small LLM Useful for Cybersecurity?
Munoz, F., Alonso, R. S., Lamo, P., & Muñoz-Babiano, A. (2026) · doi:10.1145/3793828.3793838
A Comprehensive Bibliometric Analysis of Insider Threat Scholarship
Osterritter, L. J., & Carley, K. M. (2026) · IEEE Transactions on Computational Social Systems · doi:10.1109/tcss.2026.3705576
“A more recent behavioral review advocated for the integration of sophisticated time-series techniques and natural language processing (NLP) approaches that can capture temporal patterns and contextual information in user behaviors [52].”
Cardoso, J. M. P., & Najjar, W. A. (2026) · ACM Transactions on Reconfigurable Technology and Systems · doi:10.1145/3829368
“…context of a HLS C-to-Verilog flow, approaches for HLS from Domain-Specific Languages (DSLs) , synthesis of pattern-matching rules consisting of regular expressions, frameworks, and runtime support for building multi-core FPGA SoC designs, and an HLS computer vision and image processing library.”
Cheng, K., Li, D., Tang, W., Shu, Y., & Qiang, W. (2026) · Applied Sciences · doi:10.3390/app16147054
Slim, A., Charef, M., & Maazouzi, F. (2026) · Arabian Journal for Science and Engineering · doi:10.1007/s13369-026-11520-7
Fine-Grained Insider Threat Detection Based on BDI and Scenario-Aware DBLOF
Xing, L., Zhang, H., Liu, Y., & Wang, X. (2026) · International Conference on Artificial Intelligence, Big Data and Algorithms (CAIBDA) · doi:10.1109/caibda70336.2026.11621199
“The representation is then classified by Random Forest to obtain the final insider threat detection result [6], [7].”
CLASSIFICATION OF VISITORS AND IDENTIFYING INTRUDERS IN A NETWORK
Hejazi, N., & Ozdemır, E. (2026) · International Journal of Informatics and Applied Mathematics · doi:10.53508/ijiam.1780395
Privacy Preserving Federated Learning for Insider Threat Detection
Joshi, S., Dash, A., Tiwari, P., & Krishnan, D. (2026) · Lecture notes in networks and systems · doi:10.1007/978-3-032-30005-8_26
Multi‐Agent Real‐Time Detection of Insider Threats via Collaborative Reasoning
Cheng, K., Li, D., Tang, W., Tan, L., Xiang, K., Liu, T., & Qiang, W. (2026) · Security and Privacy · doi:10.1002/spy2.70243
“In the prompts, unlike traditional rule-based methods that require exhaustive keyword definitions to filter suspicious logs [24], we only need broad descriptions to achieve excellent results with better generalization capabilities.”
Ali, I., & Madhu, B. (2026) · AIP conference proceedings · doi:10.1063/5.0329384
FSCNN-ITDNet: A Novel Framework for Insider Threat Detection via Feature Selection and 1D-CNN
Li, Y., Yang, H., Dong, T., & He, J. (2026) · IEEE International Conference on Computer Vision and Deep Learning (DLCV) · doi:10.1109/dlcv69906.2026.11635484
“The current mainstream research approach is to explore multi-dimensional insider threat detection research [9] .”
Razzaq, K., Shah, M., & Abbasi, S. I. (2026) · Asian Journal of Criminology · doi:10.1007/s11417-026-09505-4
“These technologies enable the analysis of vast datasets in real time, the identification of complex patterns indicative of malicious activity, and the adaptation to evolving threats that static, rule-based systems cannot (Alzaabi & Mehmood, 2024).”
Adaptive Behavioural Intelligent Insider Threat Detection: A Systematic ReviewPreprint
Galadima, I. B., Wahab, N. H. A., Osman, M. Z., & Danlamid, G. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7302121
Raju, K. P., & Rao, D. H. (2026) · Smart innovation, systems and technologies · doi:10.1007/978-3-032-25490-0_16
Rahman, M. M., Mekhriddin, N., Cherukuri, A. K., et al. (2026) · doi:10.1109/iccsdfai70505.2026.11648036
“Despite these advantages, detecting an insider threat is a challenging problem due to extreme imbalances between dataset classes, some similar behaviors in malicious and normal user activities, and the requirement to capture the time-dependent aspect of user activities [10].”
A systematic review on the current scenarios and future frontiers for securing smart grid systems
Sivakumar, E., Ganesan, G., Premkumar, R., Rani, R. H. J., & Srinivasan, K. (2026) · Discover Computing · doi:10.1007/s10791-026-10348-x · Cited by 2
Hybrid Ensemble Learning Model with Explainable Anomaly Detection for Insider Threat Analysis
Oommen, L., Abhinav, P., V, Indu Shree, B., & Gadde, A. (2026) · International Conference on Power, Control and Computing Technologies (ICPC2T) · doi:10.1109/icpc2t68221.2026.11646349
“GNNs are expensive and not simple to compute, although they have high potential [7].”
Rahman, M. M., & Hossain, S. (2026) · International Journal of Data Science and Analytics · doi:10.1007/s41060-026-01254-y
Kundiya, K. R., & Haribhakta, Y. V. (2026) · IEEE Access · doi:10.1109/access.2026.3726811
“Parallel to this, Natural Language Processing (NLP) methods have facilitated processing textual information, including emails and web logs, to reveal linguistic signs of sentiment, stress, or intent [5], [6].”
Adanbaev, A., & Sagymbaev, A. A. (2026) · Array · doi:10.1016/j.array.2026.101231
Wambura, S. M., Ndewingia, H. G., & TONGORA, E. F. (2026) · SSRN Electronic Journal · doi:10.2139/ssrn.7454898
Ikpe, I., Ekpah, D., & Egbe, T. I. (2026) · Springer eBooks · doi:10.1007/978-3-032-20513-1_17
Doodson, J., Caputo, D. D., & Murphy, J. F. (2026) · Computers & Security · doi:10.1016/j.cose.2026.105180
Saxena, P., Singh, S., Rawat, A., & Verma, R. (2026) · Lecture notes in electrical engineering · doi:10.1007/978-3-032-27343-7_32
A systematic review of federated learning applications in mitigating insider threats
Mdaghri, A. A., Alae, A., & Hilali, A. A. (2026) · Applied Soft Computing · doi:10.1016/j.asoc.2026.116478
Adaptive Method for Mitigating the Impact of Cyberattacks on Information Systems
Lysenko, S., ISAIEV, T., Sochor, T., et al. (2026) · International Conference on Advanced Computer Information Technologies (ACIT) · doi:10.1109/acit69831.2026.11700170
Explainable Transformer Models for Insider Threat Detection in Enterprise Systems
Al-Dhaqm, A., Bamasoud, D. M., Brnawy, R., Bamaqa, A., Alharbi, A. A., & Aljubayri, I. (2026) · Engineering Technology & Applied Science Research · doi:10.48084/etasr.21281
“PREPROCESSING Experiments use the CERT insider threat test corpus, the most widely used public benchmark in this field [4, 7, 8].”
Influential
Metadata
- Authors
- Alzaabi, F. R., & Mehmood, A.
- Affiliations
- Abu Dhabi University (AE)
- ORCID
- Mehmood, Abid
- Venue
- IEEE Access
- Published
- 2024
- Volume
- 12
- Pages
- 30907-30927
- ISSN
- 2169-3536 (ISSN-L)
- OpenAlex
- W4392151675
- Semantic Scholar
- 98b3d89075ca3345cb2cc550a9c34ab9cf9add41
- Cited by
- 204
- References
- 94
- Citations by year
- 2026: 83 · 2025: 95 · 2024: 26
- FWCI
- 76.36
- 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
- Abu Dhabi University’s Office of Research and Grant Programs
- Abu Dhabi University’s office of sponsored programs in the United Emirates funded this endeavor (19300752)
- Topics
- Physical Sciences › Computer Science › Information Systems › Information and Cyber Security
- Physical Sciences › Computer Science › Computer Networks and Communications › Network Security and Intrusion Detection
- Physical Sciences › Computer Science › Artificial Intelligence › Privacy-Preserving Technologies in Data
- Keywords
- insider threat detection, malicious insiders, privileged access, deep learning, natural language processing, large language models, time series analysis, temporal patterns, human behavior analysis, cybersecurity, information security
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.
The claim verdicts this report counts are experimental: their accuracy is not yet measured.
A language model drew the claims from the paper on 2026-10-10, under version 3 of the claim definition (model deepseek-v4.1-flash, prompt extract-v3).
A second model labelled each claim on 2026-10-10 (model jev-1.13-20260917, definition revision gold-guideline-v0.2).
Cited sources are checked with a language model’s help (gpt-6-sol and qwen3.8-omni-flash).
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.