Abstract
In this paper, we introduce a machine learning-based system that is capable of generating natural language text describing the purpose and core functionality of Android apps based on their actual code. We design a dense neural network that captures the semantic relationships of resource identifiers, string constants, and API calls contained in apps to derive a high-level picture of implemented program behavior. For arbitrary applications, our system can predict precise, human-readable keywords and short phrases that indicate the main use-cases apps are designed for.
We evaluate our solution on 67,040 real-world apps and find that with a precision between 69% and 84% we can identify keywords that also occur in the developer-provided description in Google Play. To avoid incomprehensible black box predictions, we apply a model explaining algorithm and demonstrate that our technique can substantially augment inspections of Android apps by contributing contextual information.
| Original language | English |
|---|---|
| Number of pages | 14 |
| Publication status | Accepted/In press - 2020 |
| Event | 35rd IFIP TC-11 SEC 2020 International Conference on Information Security and Privacy Protection - Maribor, Slovenia Duration: 26 May 2020 → 28 May 2020 https://sec2020.um.si |
Conference
| Conference | 35rd IFIP TC-11 SEC 2020 International Conference on Information Security and Privacy Protection |
|---|---|
| Abbreviated title | IFIP SEC 2020 |
| Country | Slovenia |
| City | Maribor |
| Period | 26/05/20 → 28/05/20 |
| Internet address |
Fingerprint
Keywords
- Android
- TF-IDF
- Deep Learning
- NLP
Cite this
Code between the Lines: Semantic Analysis of Android Applications. / Feichtner, Johannes; Gruber, Stefan.
2020. Paper presented at 35rd IFIP TC-11 SEC 2020 International Conference on Information Security and Privacy Protection , Maribor, Slovenia.Research output: Contribution to conference › Paper › Research › peer-review
}
TY - CONF
T1 - Code between the Lines: Semantic Analysis of Android Applications
AU - Feichtner, Johannes
AU - Gruber, Stefan
PY - 2020
Y1 - 2020
N2 - Static and dynamic program analysis are the key concepts researchers apply to uncover security-critical implementation weaknesses in Android applications. As it is often not obvious in which context problematic statements occur, it is challenging to assess their practical impact. While some flaws may turn out to be bad practice but not undermine the overall security level, others could have a serious impact. Distinguishing them requires knowledge of the designated app purpose.In this paper, we introduce a machine learning-based system that is capable of generating natural language text describing the purpose and core functionality of Android apps based on their actual code. We design a dense neural network that captures the semantic relationships of resource identifiers, string constants, and API calls contained in apps to derive a high-level picture of implemented program behavior. For arbitrary applications, our system can predict precise, human-readable keywords and short phrases that indicate the main use-cases apps are designed for.We evaluate our solution on 67,040 real-world apps and find that with a precision between 69% and 84% we can identify keywords that also occur in the developer-provided description in Google Play. To avoid incomprehensible black box predictions, we apply a model explaining algorithm and demonstrate that our technique can substantially augment inspections of Android apps by contributing contextual information.
AB - Static and dynamic program analysis are the key concepts researchers apply to uncover security-critical implementation weaknesses in Android applications. As it is often not obvious in which context problematic statements occur, it is challenging to assess their practical impact. While some flaws may turn out to be bad practice but not undermine the overall security level, others could have a serious impact. Distinguishing them requires knowledge of the designated app purpose.In this paper, we introduce a machine learning-based system that is capable of generating natural language text describing the purpose and core functionality of Android apps based on their actual code. We design a dense neural network that captures the semantic relationships of resource identifiers, string constants, and API calls contained in apps to derive a high-level picture of implemented program behavior. For arbitrary applications, our system can predict precise, human-readable keywords and short phrases that indicate the main use-cases apps are designed for.We evaluate our solution on 67,040 real-world apps and find that with a precision between 69% and 84% we can identify keywords that also occur in the developer-provided description in Google Play. To avoid incomprehensible black box predictions, we apply a model explaining algorithm and demonstrate that our technique can substantially augment inspections of Android apps by contributing contextual information.
KW - Android
KW - TF-IDF
KW - Deep Learning
KW - NLP
M3 - Paper
ER -