Identifying Malicious Network Traffic Detection using Graph Transformers & Masked Autoencoders
Bibliographic record
Abstract
The rise in cyber-attacks highlights the critical need for advanced network intrusion detection systems.Traditional machine learning methods often fail to capture the complex patterns inherent in cybersecurity data.Graph Neural Networks (GNNs) [4], capable of efficiently modeling data as nodes and edges, have shown promise in addressing these challenges.This research proposes a novel approach combining Graph Masked Autoencoder (Graph MAE) [2] for self-supervised pretraining and a global attention-based Graph Transformer (Graph GPS) [3] for fine-tuning.Utilizing the UNSW-NB15 dataset [1], we sampled 25% of the dataset (approximately 653,012 network flow records) due to computational restraints.Performance metrics such as Accuracy, Precision, Recall, F1-score, and Area Under the ROC Curve (AUC) were employed.Results indicate significant performance improvements (Accuracy: 0.95, Precision: 0.58, Recall: 0.94, F1-score: 0.72, AUC: 0.98) compared to a baseline two-layer Graph Convolution Network (GCN) [4] model.The study underscores the efficacy of combining self-supervised learning methods and global attention mechanisms in enhancing malicious traffic 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 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.003 |
| Science and technology studies | 0.001 | 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 itClassification
machine, unvalidatedMachine predicted; a candidate call from one teacher head, 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".