Explainable Bidirectional LSTM Autoencoder for Insider Threat Detection in Various Scenarios
Bibliographic record
Abstract
Insider threats remain difficult to detect due to their legitimate access and subtle behavioral shifts. We present an explainable anomaly detection framework based on a Bidirectional LSTM Autoencoder trained on daily user activity sequences from CERT v5.2. The model learns to reconstruct normal behavior and flags high reconstruction error sequences as anomalies. To address the opacity of deep models, we introduce a surrogate Random Forest trained on human-interpretable temporal and behavioral features, enabling SHAP-based explanations. SHAP summary and waterfall plots reveal both global and instancelevel insights, enhancing Security Operations Center (SOC) trust and usability. While our system prioritizes high recall to minimize missed threats, SHAP explanations provide analysts with rapid visual insights into feature contributions, supporting the identification and dismissal of false positives. We evaluate our system across four insider threat scenarios, demonstrating strong alignment between flagged anomalies and known malicious behaviors. Our framework achieves high precision and recall while maintaining interpretability, bridging the gap between performance and transparency in real-world security environments.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
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.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
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".