MétaCan
Menu
Back to cohort
Record W7162471993 · doi:10.65521/ijeecs.v14i2.2102

A Comprehensive Review of Graph Neural Networks for Malware Classification Pipelines: Architectures, Robustness, and Intelligent Security Applications

2025· article· W7162471993 on OpenAlex

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

VenueInternational Journal of Electrical Electronics and Computer Systems · 2025
Typearticle
Language
FieldComputer Science
TopicAdvanced Graph Neural Networks
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsMalwareAdversarial systemConvolutional neural networkRobustness (evolution)GraphFeature learningDeep learningArtificial neural network

Abstract

fetched live from OpenAlex

The rapid evolution of cyber threats, particularly malware, has driven the need for advanced detection and classification techniques capable of handling complex and dynamic attack patterns. Traditional signature-based and heuristic approaches are increasingly ineffective against polymorphic and zero-day malware, creating a demand for more adaptive solutions. In this context, Graph Neural Networks (GNNs) have emerged as a powerful paradigm for modeling structured relationships in malware data, including function call graphs, network traffic flows, and system interactions. Unlike conventional machine learning models, GNNs capture non-Euclidean relationships, enabling superior representation learning and improved classification accuracy. This review analyzes GNN-based malware classification pipelines, focusing on architectural designs, robustness strategies, and security applications. It highlights the integration of graph construction methods, feature extraction, and classification models, while also examining issues such as adversarial robustness, scalability, and explainability. Findings suggest that models like Graph Convolutional Networks, Graph Attention Networks, and hybrid approaches outperform traditional deep learning techniques by leveraging relational dependencies. Despite their promise, challenges such as computational overhead, dataset limitations, and adversarial vulnerabilities remain, indicating the need for lightweight, interpretable, and privacy-preserving GNN frameworks.

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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow)
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.828
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0010.001
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0010.000
Research integrity0.0000.001
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 head0.014
GPT teacher head0.287
Teacher spread0.272 · 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