MétaCan
Menu
Back to cohort

Explicit Behavioral Embedding Method for Generating Explanations of Insider Threat Events

2025· article· W4417470884 on OpenAlexaff
Abdul Muqtadir Abbasi, Fariha Muqtadir, Otman Basir, Shi Cao

Bibliographic record

Venuenot available
Typearticle
Language
FieldComputer Science
TopicInformation and Cyber Security
Canadian institutionsUniversity of Waterloo
Fundersnot available
KeywordsInsider threatInsiderAnomaly detectionTransparency (behavior)Software deploymentCluster analysisEmbeddingFalse positive paradoxDeception

Abstract

fetched live from OpenAlex

Insider threats pose significant risks to organizational security; however, many detection models lack transparency, which hinders their practical deployment due to high false-positive rates. We propose a novel framework that integrates behavioral embeddings with SHAP (Shapley Additive Explanations) to enhance the explainability of unsupervised anomaly detection models. By modeling temporal and semantic aspects of user actions, our approach generates interpretable visualizations of anomalous behaviors. Applied to the CERT v4.2 Insider Threat Dataset, the framework effectively identifies and explains anomalies, such as unauthorized data transfers and malicious system activities, through clustering and feature-importance analysis. Our results demonstrate that explainable models help reduce analyst workload by filtering false positives and providing actionable insights. This approach enhances decision-making, facilitates compliance with transparency regulations such as GDPR, and addresses the trade-off between detection accuracy and interpretability, making it a valuable tool for real-world insider threat detection.

Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.

How this classification was reachedexpand

Full frame distilled prediction

Teacher imitation

Not calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.

metaresearch head score (Codex)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.965
Threshold uncertainty score0.958

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.001
Open science0.0010.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

Machine scores (provisional)

The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.

Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.

Opus teacher head0.048
GPT teacher head0.388
Teacher spread0.339 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

The models applied no category: nothing in the taxonomy fit this work.
Study designSimulation or modeling
Domainnot available
GenreMethods

How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".

Quick stats

Citations0
Published2025
Admission routes1
Has abstractyes

Explore more

Same topicInformation and Cyber SecurityFrench-language works237,207