XAPT: Explainable Anomaly-Driven Prediction of Threat Stages in APT Campaigns
Bibliographic record
Abstract
Advanced Persistent Threats (APTs) are long-lived, targeted cyberattacks that progress through multiple stages, characterized by strong stealth and intent. To achieve accurate and interpretable stage-level prediction, we propose XAPT, an eXplainable, anomaly-driven framework for APT campaign analysis. XAPT is centered on three key innovations. First, we derive PCA-based reconstruction errors and transform them into calibrated probabilistic anomaly scores, enabling principled quantification of the event abnormality. Second, these calibrated scores are incorporated into a Bayesian Network-based multiclass classifier for cyber-kill-chain stage inference, capturing uncertainty and inter-feature dependencies. Third, SHAP-based feature attribution reveals how anomaly scores and other features contribute to classification outcomes, offering transparent and analytically friendly explanations. Evaluation of two public datasets shows that XAPT achieves high stage-level detection accuracy while producing actionable feature-level interpretations that support operational analysis. By unifying calibrated anomaly scoring, Bayesian inference, and SHAP explanation, XAPT offers a comprehensive and interpretable solution for advanced 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 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 | 0.002 | 0.009 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.002 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 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".