BrainShield: A Hybrid Machine Learning-Based Malware Detection Model for Android Devices
Bibliographic record
Abstract
Android has become the leading operating system for mobile devices, and the most targeted one by malware. Therefore, many analysis methods have been proposed for detecting Android malware. However, few of them use proper datasets for evaluation. In this paper, we propose BrainShield, a hybrid malware detection model trained on the Omnidroid dataset to reduce attacks on Android devices. The latter is the most diversified dataset in terms of the number of different features, and contains the largest number of samples, 22,000 samples, for model evaluation in the Android malware detection field. BrainShield’s implementation is based on a client/server architecture and consists of three fully connected neural networks: (1) the first is used for static analysis and reaches an accuracy of 92.9% trained on 840 static features; (2) the second is a dynamic neural network that reaches an accuracy of 81.1% trained on 3722 dynamic features; and (3) the third neural network proposed is hybrid, reaching an accuracy of 91.1% trained on 7081 static and dynamic features. Simulation results show that BrainShield is able to improve the accuracy and the precision of well-known malware detection methods.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.001 | 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".