Android malicious attacks detection models using machine learning techniques based on permissions
Bibliographic record
Abstract
The Android operating system is the most used mobile operating system in the world, and it is one of the most popular operating systems for different kinds of devices from smartwatches, IoT, and TVs to mobiles and cockpits in cars. Security is the main challenge to any operating system. Android malware attacks and vulnerabilities are known as emerging risks for mobile devices. The development of Android malware has been observed to be at an accelerated speed. Most Android security breaches permitted by permission misuse are amongst the most critical and prevalent issues threatening Android OS security. This research performs several studies on malware and non-malware applications to provide a recently updated dataset. The goal of proposed models is to find a combination of noise-cleaning algorithms, features selection techniques, and classification algorithms that are noise-tolerant and can achieve high accuracy results in detecting new Android malware. The results from the empirical experiments show that the proposed models are able to detect Android malware with an accuracy that reaches 87%, despite the noise in the dataset. We also find that the best classification results are achieved using the RF algorithm. This work can be extended in many ways by applying higher noise ratios and running more classifiers and optimizers.
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 | 0.003 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| 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) | 0.001 | 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".