DroidARA: Android Application Automatic Categorization Based on API Relationship Analysis

被引:2
作者
Fan, Wenhao [1 ]
Chen, Ye [1 ]
Liu, Yuan'an [1 ]
Wu, Fan [1 ]
机构
[1] Beijing Univ Posts & Telecommun, Sch Elect Engn, Beijing Key Lab Work Safety Intelligent Monitorin, Beijing 100876, Peoples R China
关键词
Android; categorization; API relationship; static analysis;
D O I
10.1109/ACCESS.2019.2948212
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
An application (app) market with well -managed categorization will help users with app search and recommendation. Current categorization methods in app markets mainly rely on manual operation. Existing approaches for automatic Android app categorization suffer from low efficiency and low accuracy due to insufficient analysis of features, or inappropriate choice of features. This will mislead users to download unrelated apps and is not conducive to market stability maintenance. In this paper, we propose DroidARA, an efficient automatic categorization method for Android apps based on API relationships analysis. Considering that the app category can be characterized by API relationships which represent the combinations and links among APIs, we design a complete system to generate API call graphs, extract the API relationships information, transform them into feature vectors and train the classifier. Firstly, the API calls are obtained through static analysis to generate API call graphs that contain the relationships among APIs. A novel matrix structure as well as related algorithm are designed to extract the API relationships information from API call graphs. After that, the matrix is transformed into vector according to two feature selection methods we designed for strengthening the use of effective information in the API relationships. A convolutional neural network (CNN) model is then trained with labeled samples of such feature vectors. To validate the feasibility of DroidARA, we conduct several categorization experiments on 19949 real apps of Google Play. The results demonstrate that DroidARA can achieve an average 88.9% accuracy in categorizing the apps into 24 categories, which outperforms existing methods by 18.5%.
引用
收藏
页码:157987 / 157996
页数:10
相关论文
共 22 条
[1]   Clustering Mobile Apps Based on Mined Textual Features [J].
Al-Subaihin, A. A. ;
Sarro, F. ;
Black, S. ;
Capra, L. ;
Harman, M. ;
Jia, Y. ;
Zhang, Y. .
ESEM'16: PROCEEDINGS OF THE 10TH ACM/IEEE INTERNATIONAL SYMPOSIUM ON EMPIRICAL SOFTWARE ENGINEERING AND MEASUREMENT, 2016,
[2]  
Android Developers, APPL FUND
[3]  
[Anonymous], 2019, SMARTPHONE OS MARKET
[4]  
AppBrain, 2019, ANDR APPS GOGGL PLAY
[5]  
Au Y. F., 2012, P 2012 ACM C COMP CO, P217, DOI 10.1145/2382196.2382222
[6]   Learning Mobile App Embeddings Using Multi-task Neural Network [J].
Bajaj, Ahsaas ;
Krishna, Shubham ;
Tiwari, Hemant ;
Vala, Vanraj .
NATURAL LANGUAGE PROCESSING AND INFORMATION SYSTEMS (NLDB 2019), 2019, 11608 :29-40
[7]   Wise Mobile Icons Organization: Apps Taxonomy Classification Using Functionality Mining to Ease Apps Finding [J].
Ben Lulu, David Lavid ;
Kuflik, Tsvi .
MOBILE INFORMATION SYSTEMS, 2016, 2016
[8]   Multi-Store Metadata-Based Supervised Mobile App Classification [J].
Berardi, Giacomo ;
Esuli, Andrea ;
Fagni, Tiziano ;
Sebastiani, Fabrizio .
30TH ANNUAL ACM SYMPOSIUM ON APPLIED COMPUTING, VOLS I AND II, 2015, :585-588
[9]  
BISHOP C. M., 2006, Pattern recognition and machine learning, DOI [DOI 10.1117/1.2819119, 10.1007/978-0-387-45528-0]
[10]  
Dong F, 2016, INT CONF CLOUD COMPU, P77, DOI 10.1109/CCIS.2016.7790228