TY - GEN
T1 - Characterizing promotional attacks in mobile app store
AU - Sun, Bo
AU - Luo, Xiapu
AU - Akiyama, Mitsuaki
AU - Watanabe, Takuya
AU - Mori, Tatsuya
PY - 2017/1/1
Y1 - 2017/1/1
N2 - 2017. Mobile app stores, such as Google Play, play a vital role in the ecosystem of mobile apps. When users look for an app of interest, they can acquire useful data from the app store to facilitate their decision on installing the app or not. This data includes ratings, reviews, number of installs, and the category of the app. The ratings and reviews are the user-generated content (UGC) that affect the reputation of an app. Unfortunately, miscreants also exploit such channels to conduct promotional attacks (PAs) that lure victims to install malicious apps. In this paper, we propose and develop a new system called PADetective to detect miscreants who are likely to be conducting promotional attacks. Using a dataset with 1,723 of labeled samples, we demonstrate that the true positive rate of detection model is 90%, with a false positive rate of 5.8%. We then applied PADetective to a large dataset for characterizing the prevalence of PAs in the wild and find 289 K potential PA attackers who posted reviews to 21 K malicious apps.
AB - 2017. Mobile app stores, such as Google Play, play a vital role in the ecosystem of mobile apps. When users look for an app of interest, they can acquire useful data from the app store to facilitate their decision on installing the app or not. This data includes ratings, reviews, number of installs, and the category of the app. The ratings and reviews are the user-generated content (UGC) that affect the reputation of an app. Unfortunately, miscreants also exploit such channels to conduct promotional attacks (PAs) that lure victims to install malicious apps. In this paper, we propose and develop a new system called PADetective to detect miscreants who are likely to be conducting promotional attacks. Using a dataset with 1,723 of labeled samples, we demonstrate that the true positive rate of detection model is 90%, with a false positive rate of 5.8%. We then applied PADetective to a large dataset for characterizing the prevalence of PAs in the wild and find 289 K potential PA attackers who posted reviews to 21 K malicious apps.
KW - Machine learning
KW - Mobile app store
KW - Promotional attacks
UR - http://www.scopus.com/inward/record.url?scp=85022179732&partnerID=8YFLogxK
U2 - 10.1007/978-981-10-5421-1_10
DO - 10.1007/978-981-10-5421-1_10
M3 - Conference article published in proceeding or book
SN - 9789811054204
T3 - Communications in Computer and Information Science
SP - 113
EP - 127
BT - Applications and Techniques in Information Security - 8th International Conference, ATIS 2017, Proceedings
PB - Springer Verlag
T2 - 8th International Conference on Applications and Techniques in Information Security, ATIS 2017
Y2 - 6 July 2017 through 7 July 2017
ER -