A Comparative Study on Malware Detection Using Supervised Machine Learning Models
Bibliographic record
Abstract
Traditional signature-based systems struggle to detect novel and variably structures threats such as polymorphic and metamorphic malware. These systems rely on predefined rules, which limit their ability to identify newly developed, obfuscated, or zero-day attacks. Given the constantly evolving nature of cyber threats, it is crucial to develop detection systems capable of identifying malicious behavior without relying solely on static signatures. This study investigates the effectiveness of supervised machine learning (ML) techniques in detecting malware. It uses the Canadian Institute for Cybersecurity Intrusion Detection System 2017 (CICIDS2017) dataset which includes both attacks and benign traffic. Four widely used supervised models, Random Forest, Support Vector Machine (SVM), K-Nearest Neighbors (KNN) and XGBoost, are evaluated and compared.Each model undergoes the same data preparation process, including features selection and data balancing, to ensure fair performance assessment. Model Performance is evaluated using standard metrics such as accuracy, precision, recall and F1-score. Among the models, Random Forest achieved the highest accuracy of approximately 99.8%, demonstrating strong robustness and generalizability. XGBoost followed with a commendable accuracy of around 92%, offering a balance between computational efficiency and interpretability. In contrast, SVM and KNN exhibited limitations in detecting minority attack classes. Overall, the Random Forest model outperformed other established methods. Feature importance analysis revealed that attributes such as Avg Bwd Segment Size and Flow IAT Max significantly contribute to the detection of malicious traffic.
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) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.001 | 0.003 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| 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".