MétaCan
Menu
Back to cohort

P-Code Based Classification to Detect Malicious VBA Macro

2020· article· en· W3114105288 on OpenAlex
Simon Huneault-LeBlanc, Chamseddine Talhi

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.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Malware Detection Techniques
Canadian institutionsÉcole de Technologie Supérieure
Fundersnot available
KeywordsMalwareComputer scienceOpcodeMacroCode (set theory)HeuristicsObfuscationArtificial intelligenceVisual Basic for ApplicationsMachine learningPreprocessorSource codeData miningComputer securityProgramming languageOperating system

Abstract

fetched live from OpenAlex

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 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)0.000
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: Bench or experimental · Consensus signal: none
GenreCandidate signal: Methods · Consensus signal: Methods
Teacher disagreement score0.603
Threshold uncertainty score0.460

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
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 head0.038
GPT teacher head0.284
Teacher spread0.246 · 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

Quick stats

Citations10
Published2020
Admission routes1
Has abstractyes

Explore more

Same topicAdvanced Malware Detection TechniquesFrench-language works237,207