Random Forest Classification for Detecting Android Malware
Bibliographic record
Abstract
Internet connected smartphone devices play a crucial role in the application domain of Internet of Things. These devices are being widely used for day-to-day activities such as remotely controlling lighting and heating at homes, paying for parking, and recently for paying for goods using saved credit card information using Near Field Communication (NFC). Android is the most popular smartphone platform today. It is also the choice of malware authors to obtain secure and private data. In this paper we exclusively apply the machine learning ensemble learning algorithm Random Forest supervised classifier on an Android feature dataset of 48919 points of 42 features each. Our goal was to measure the accuracy of Random Forest in classifying Android application behavior to classify applications as malicious or benign. Moreover, we wanted to focus on detection accuracy as the free parameters of the Random Forest algorithm such as the number of trees, depth of each tree and number of random features selected are varied. Our experimental results based on 5-fold cross validation of our dataset shows that Random Forest performs very well with an accuracy of over 99 percent in general, an optimal Out-Of-Bag (OOB) error rate [3] of 0.0002 for forests with 40 trees or more, and a root mean squared error of 0.0171 for 160 trees.
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 | 0.003 | 0.006 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 0.001 |
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".