31Graph-ensemble methods for generating malware behavioral signatures
Bibliographic record
Abstract
In recent years, malware malware detection has significantly benefited from advanced machine learning techniques, particularly natural language processing (NLP) natural language processing (NLP) and graph neural networks (GNNs). This research presents an innovative ensemble method utilizing GNNs to generate accurate malware behavioral signatures based on process API call sequences. The approach combines models trained on different event types, such as file system, process/thread, and registry activities, into an ensemble to enhance detection accuracy. By leveraging NLP techniques like n -grams and tf-idf for API sequence vectorization, this method captures rare and critical behavioral patterns in malware malware execution. The results show improved performance over traditional models, with ensemble graph models yielding high classification accuracy and F 1 scores. Further, GNNExplainer is employed to automate the generation of API signatures, correlating them with known MITRE ATT&CK MITRE ATT&CK techniques. This study’s findings demonstrate that the proposed graph-ensemble approach can effectively identify complex malware behaviors, outperforming existing detection methods while providing interpretable insights for cybersecurity analysts.
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 | 0.000 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.009 | 0.006 |
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".