Code between the Lines: Semantic Analysis of Android Applications

Johannes Feichtner; Stefan Gruber

doi:10.1007/978-3-030-58201-2_12

Code between the Lines: Semantic Analysis of Android Applications

Johannes Feichtner^*, Stefan Gruber

^*Corresponding author for this work

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Abstract

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.

Original language	English
Title of host publication	ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings
Editors	Marko Hölbl, Tatjana Welzer, Kai Rannenberg
Place of Publication	Cham
Publisher	Springer International Publishing AG
Pages	171-186
Number of pages	16
Volume	580
ISBN (Electronic)	978-3-030-58201-2
ISBN (Print)	978-3-030-58200-5
DOIs	https://doi.org/10.1007/978-3-030-58201-2_12
Publication status	Published - Sep 2020
Event	35th International Conference on ICT Systems Security and Privacy Protection - Maribor, Slovenia Duration: 21 Sep 2020 → 23 Sep 2020 https://sec2020.um.si

Publication series

Name	IFIP Advances in Information and Communication Technology
Volume	580 IFIP
ISSN (Print)	1868-4238
ISSN (Electronic)	1868-422X

Conference

Conference	35th International Conference on ICT Systems Security and Privacy Protection
Abbreviated title	IFIP SEC 2020
Country	Slovenia
City	Maribor
Period	21/09/20 → 23/09/20
Internet address	https://sec2020.um.si

Keywords

Android
TF-IDF
Deep Learning
NLP

ASJC Scopus subject areas

Information Systems and Management
Information Systems
Computer Networks and Communications

Access to Document

10.1007/978-3-030-58201-2_12

mainAccepted author manuscript, 535 KB

Cite this

Feichtner, J., & Gruber, S. (2020). Code between the Lines: Semantic Analysis of Android Applications. In M. Hölbl, T. Welzer, & K. Rannenberg (Eds.), ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings (Vol. 580, pp. 171-186). (IFIP Advances in Information and Communication Technology; Vol. 580 IFIP). Springer International Publishing AG . https://doi.org/10.1007/978-3-030-58201-2_12

Code between the Lines: Semantic Analysis of Android Applications. / Feichtner, Johannes; Gruber, Stefan.

ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings. ed. / Marko Hölbl; Tatjana Welzer; Kai Rannenberg. Vol. 580 Cham : Springer International Publishing AG , 2020. p. 171-186 (IFIP Advances in Information and Communication Technology; Vol. 580 IFIP).

Research output: Chapter in Book/Report/Conference proceeding › Conference paper › peer-review

Feichtner, J & Gruber, S 2020, Code between the Lines: Semantic Analysis of Android Applications. in M Hölbl, T Welzer & K Rannenberg (eds), ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings. vol. 580, IFIP Advances in Information and Communication Technology, vol. 580 IFIP, Springer International Publishing AG , Cham, pp. 171-186, 35th International Conference on ICT Systems Security and Privacy Protection, Maribor, Slovenia, 21/09/20. https://doi.org/10.1007/978-3-030-58201-2_12

Feichtner J, Gruber S. Code between the Lines: Semantic Analysis of Android Applications. In Hölbl M, Welzer T, Rannenberg K, editors, ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings. Vol. 580. Cham: Springer International Publishing AG . 2020. p. 171-186. (IFIP Advances in Information and Communication Technology). https://doi.org/10.1007/978-3-030-58201-2_12

Feichtner, Johannes ; Gruber, Stefan. / Code between the Lines: Semantic Analysis of Android Applications. ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings. editor / Marko Hölbl ; Tatjana Welzer ; Kai Rannenberg. Vol. 580 Cham : Springer International Publishing AG , 2020. pp. 171-186 (IFIP Advances in Information and Communication Technology).

@inproceedings{77316b358edd4f85a7e5426b43ba1d98,

title = "Code between the Lines: Semantic Analysis of Android Applications",

abstract = "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.",

keywords = "Android, TF-IDF, Deep Learning, NLP",

author = "Johannes Feichtner and Stefan Gruber",

year = "2020",

month = sep,

doi = "10.1007/978-3-030-58201-2_12",

language = "English",

isbn = "978-3-030-58200-5",

volume = "580",

series = "IFIP Advances in Information and Communication Technology",

publisher = "Springer International Publishing AG ",

pages = "171--186",

editor = "Marko H{\"o}lbl and Tatjana Welzer and Kai Rannenberg",

booktitle = "ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings",

address = "Switzerland",

note = "35th International Conference on ICT Systems Security and Privacy Protection, IFIP SEC 2020 ; Conference date: 21-09-2020 Through 23-09-2020",

url = "https://sec2020.um.si",

}

TY - GEN

T1 - Code between the Lines: Semantic Analysis of Android Applications

AU - Feichtner, Johannes

AU - Gruber, Stefan

PY - 2020/9

Y1 - 2020/9

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

UR - http://www.scopus.com/inward/record.url?scp=85092100355&partnerID=8YFLogxK

U2 - 10.1007/978-3-030-58201-2_12

DO - 10.1007/978-3-030-58201-2_12

M3 - Conference paper

SN - 978-3-030-58200-5

VL - 580

T3 - IFIP Advances in Information and Communication Technology

SP - 171

EP - 186

BT - ICT Systems Security and Privacy Protection - 35th IFIP TC 11 International Conference, SEC 2020, Proceedings

A2 - Hölbl, Marko

A2 - Welzer, Tatjana

A2 - Rannenberg, Kai

PB - Springer International Publishing AG

CY - Cham

T2 - 35th International Conference on ICT Systems Security and Privacy Protection

Y2 - 21 September 2020 through 23 September 2020

ER -

Code between the Lines: Semantic Analysis of Android Applications

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

A-SIT - Secure Information Technology Center Austria

Cite this

Code between the Lines: Semantic Analysis of Android Applications

Abstract

Publication series

Conference

Keywords

ASJC Scopus subject areas

Access to Document

Other files and links

Fingerprint

Projects

A-SIT - Secure Information Technology Center Austria

Cite this