Automatic Components Separation of Obfuscated Android Applications: An Empirical Study of Design Based Features
Bibliographic record
Abstract
In modern days, mobile applications (apps) have become omnipresent. Components of mobile apps (such as 3rd party libraries) require to be separated and analyzed differently for security issue detection, repackaged app detection, tumor code purification and so on. Various techniques are available to automatically analyze mobile apps. However, analysis of the app's executable binary remains challenging due to required curated database, large codebases and obfuscation. Considering these, we focus on exploring a versatile technique to separate different components with design-based features independent of code obfuscation. Particularly, we conducted an empirical study using design patterns and fuzzy signatures to separate app components such as 3rd party libraries. In doing so, we built a system for automatically extracting design patterns from both the executable package (APK) and Jar of an Android application. The experimental results with various standard datasets containing 3rd party libraries, obfuscated apps and malwares reveal that design features like these are present significantly within them (within 60% APKs including malware). Moreover, these features remain unaltered even after app obfuscation. Finally, as a case study, we found that the design patterns alone can detect 3rd party libraries within the obfuscated apps considerably (F1 score is 32%). Overall, our empirical study reveals that design features might play a versatile role in separating various Android components for various purposes.
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 | 0.003 | 0.022 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.002 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 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 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".