AdStop: Efficient flow-based mobile adware detection using machine learning
Bibliographic record
Abstract
In recent years, mobile devices have become commonly used not only for voice communications but also to play a major role in our daily activities. Accordingly, the number of mobile users and the number of mobile applications (apps) have increased exponentially. With a wide user base exceeding 2 billion users, Android is the most popular operating system worldwide, which makes it a frequent target for malicious actors. Adware is a form of malware that downloads and displays unwanted advertisements, which are often offensive and always unsolicited. This paper presents a machine learning-based system (AdStop) that detects Android adware by examining the features in the flow of network traffic. The design goals of AdStop are high accuracy, high speed, and good generalizability beyond the training dataset. A feature reduction stage was implemented to increase the accuracy of Adware detection and reduce the time overhead. The number of relevant features used in training was reduced from 79 to 13 to improve the efficiency and simplify the deployment of AdStop. In experiments, the tool had an accuracy of 98.02% with a false positive rate of 2% and a false negative rate of 1.9%. The time overhead was 5.54 s for training and 9.36 µs for a single instance in the testing phase. In tests, AdStop outperformed other methods described in the literature. It is an accurate and lightweight tool for detecting mobile adware.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.003 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.002 |
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".