A Client/Server Malware Detection Model Based on Machine Learning for Android Devices
Bibliographic record
Abstract
The rapid adoption of Android devices comes with the growing prevalence of mobile malware, which leads to serious threats to mobile phone security and attacks private information on mobile devices. In this paper, we designed and implemented a model for malware detection on Android devices to protect private and financial information, for the mobile applications of the ATISCOM project. This model is based on client/server architecture, to reduce the heavy computations on a mobile device by sending data from the mobile device to the server for remote processing (i.e., offloading) of the predictions. We then gradually optimized our proposed model for better classification of the newly installed applications on Android devices. We at first adopted Naive Bayes to build the model with 92.4486% accuracy, then the classification method that gave the best accuracy of 93.85% for stochastic gradient descent (SGD) with binary class (i.e., malware and benign), and finally the regression method with numerical values ranging from −100 to 100 to manage the uncertainty predictions. Therefore, our proposed model with random forest regression gives a good accuracy in terms of performance, with a good correlation coefficient, minimum computation time and the smallest number of errors for malware 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 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 | 0.001 | 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 | 0.001 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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".