P-Code Based Classification to Detect Malicious VBA Macro
Why this work is in the frame
A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.
Bibliographic record
Abstract
VBA macro malware has seen a resurgence of use in recent years by malicious actors as a vector to perpetrate cyber attacks. Anti-virus and analysis tools use heuristics of the VBA source code in an effort to detect such attacks. Although efficient, anti-virus and analysis tools are not able to detect macro malware based on VBA opcode (p-code). This gap requires further research in using p-code for macro malware detection. In this paper, we discuss the extraction of p-code within macro based documents and present the classification of benign and malicious p-code using five learning classifiers. Our method selects 12 specific p-code features and use them to train the classifiers. Our approach obtained a high accuracy (98.8%) and is promising for macro malware detection in real-world applications. We have discussed the challenges our approach could face and their potential solutions. To promote future studies in this field, we have made our dataset available to the community.
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.
Full frame distilled prediction
Teacher imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 it