A Comparative Analysis of Properties that May be Used for Malware Detection
Bibliographic record
Abstract
Despite detection efforts, malware regularly makes its way onto online markets for mobile applications. There are a variety of known methods that malware developers use to disguise the intent of their applications from anti-malware software. These methods include features that can be discovered by examining the code, such as obfuscation. As such, one might try to discover malware by looking directly for these particular code features. Unfortunately, the features used by malware developers may also appear in benign applications for legitimate reasons. In order to determine if these features are effective for evasion of malware detection, we therefore need to perform a comparative analysis to see which features are more commonly associated with malware. In this manner, we try to determine if there are any specific code features that can be associated with malware that gets past existing filters. We focus in particular on the Google Play Store, and the Google Play Protect system. We consider eight different code features that could be used to reduce the effectiveness of Android malware analysis tools. By comparing malware samples and non-malware samples from the Google Play Store, we try to determine if any of these features is associated more closely with malware that has escaped detection. This is a description of work in progress, to demonstrate the utility of the approach.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".