Android Malware Classification Using Gain Ratio and Ensembled Machine Learning
Bibliographic record
Abstract
Recently, the number of Android users has significantly increased, which has made Android a target for attackers to launch their malicious activities.Malware or malicious code is often embedded in Android apps to gain access to the user's device and retrieve personal data.Researchers have explored various approaches to mitigate the spread of Android malware.Besides, the Android malware dataset has huge dimensions with hundreds of features.Choosing the proper feature selection method is one of the challenges for producing a reliable detection model.This paper proposes an approach to detecting Android malware and classifying it into five categories using gain ratio feature selection and an ensemble machine learning algorithm.Features are reduced based on their importance value through the gain ratio calculation method.Then, features that are considered necessary are included in a classification process that combines many models.Experiment using the CICMalDroid2020 (Canadian Institute for Cybersecurity Malware of Android 2020) dataset shows that the proposed approach can improve detection performance.Gain ratio feature selection improves the detection accuracy in several machine learning classification algorithms, 2.59% in Naï ve Bayes, 0.90% in 𝑘-Nearest Neighbor, and 2.29% in Support Vector Machine.Thus, the ensembled machine learning models of Random Forest, Extra Tree, and k-Nearest Neighbors achieved the highest performance, with an accuracy of 94.57% and a precision score of 94.71%.
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 machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.004 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.002 | 0.001 |
| Bibliometrics | 0.004 | 0.002 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 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 source (direct Gemma or distilled Codex), 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".