Abstract
Although mobile ad frauds have been widespread, state-of-the-art approaches in the literature have mainly focused on detecting the so-called static placement frauds, where only a single UI state is involved and can be identified based on static information such as the size or location of ad views. Other types of fraud exist that involve multiple UI states and are performed dynamically while users interact with the app. Such dynamic interaction frauds, although now widely spread in apps, have not yet been explored nor addressed in the literature. In this work, we investigate a wide range of mobile ad frauds to provide a comprehensive taxonomy to the research community. We then propose, FraudDroid, a novel hybrid approach to detect ad frauds in mobile Android apps. Fraud- Droid analyses apps dynamically to build UI state transition graphs and collects their associated runtime network traffics, which are then leveraged to check against a set of heuristic-based rules for identifying ad fraudulent behaviours. We show empirically that FraudDroid detects ad frauds with a high precision (∼93%) and recall (∼92%). Experimental results further show that FraudDroid is capable of detecting ad frauds across the spectrum of fraud types. By analysing 12,000 ad-supported Android apps, FraudDroid identified 335 cases of fraud associated with 20 ad networks that are further confirmed to be true positive results and are shared with our fellow researchers to promote advanced ad fraud detection.
| Original language | English |
|---|---|
| Title of host publication | ESEC/FSE'18 - Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering |
| Subtitle of host publication | November 4–9, 2018 Lake Buena Vista, FL, USA |
| Editors | Gary T. Leavens, Alessandro Garcia, Corina S. Pasareanu |
| Place of Publication | New York NY USA |
| Publisher | Association for Computing Machinery (ACM) |
| Pages | 257-268 |
| Number of pages | 12 |
| ISBN (Electronic) | 9781450355735 |
| DOIs | |
| Publication status | Published - 2018 |
| Event | Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2018 - Lake Buena Vista, United States of America Duration: 4 Nov 2018 → 9 Nov 2018 Conference number: 26th https://conf.researchr.org/home/fse-2018 |
Conference
| Conference | Joint Meeting of the European Software Engineering Conference and the ACM SIGSOFT Symposium on the Foundations of Software Engineering 2018 |
|---|---|
| Abbreviated title | ESEC/FSE 2018 |
| Country | United States of America |
| City | Lake Buena Vista |
| Period | 4/11/18 → 9/11/18 |
| Internet address |
Keywords
- ad fraud
- Android
- automation
- mobile app
- user interface
Cite this
}
FraudDroid : automated ad fraud detection for android apps. / Dong, Feng; Wang, Haoyu; Li, Li; Guo, Yao; Bissyandé, Tegawendé F.; Liu, Tianming; Xu, Guoai; Klein, Jacques.
ESEC/FSE'18 - Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering: November 4–9, 2018 Lake Buena Vista, FL, USA. ed. / Gary T. Leavens; Alessandro Garcia; Corina S. Pasareanu. New York NY USA : Association for Computing Machinery (ACM), 2018. p. 257-268.Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review
TY - GEN
T1 - FraudDroid
T2 - automated ad fraud detection for android apps
AU - Dong, Feng
AU - Wang, Haoyu
AU - Li, Li
AU - Guo, Yao
AU - Bissyandé, Tegawendé F.
AU - Liu, Tianming
AU - Xu, Guoai
AU - Klein, Jacques
PY - 2018
Y1 - 2018
N2 - Although mobile ad frauds have been widespread, state-of-the-art approaches in the literature have mainly focused on detecting the so-called static placement frauds, where only a single UI state is involved and can be identified based on static information such as the size or location of ad views. Other types of fraud exist that involve multiple UI states and are performed dynamically while users interact with the app. Such dynamic interaction frauds, although now widely spread in apps, have not yet been explored nor addressed in the literature. In this work, we investigate a wide range of mobile ad frauds to provide a comprehensive taxonomy to the research community. We then propose, FraudDroid, a novel hybrid approach to detect ad frauds in mobile Android apps. Fraud- Droid analyses apps dynamically to build UI state transition graphs and collects their associated runtime network traffics, which are then leveraged to check against a set of heuristic-based rules for identifying ad fraudulent behaviours. We show empirically that FraudDroid detects ad frauds with a high precision (∼93%) and recall (∼92%). Experimental results further show that FraudDroid is capable of detecting ad frauds across the spectrum of fraud types. By analysing 12,000 ad-supported Android apps, FraudDroid identified 335 cases of fraud associated with 20 ad networks that are further confirmed to be true positive results and are shared with our fellow researchers to promote advanced ad fraud detection.
AB - Although mobile ad frauds have been widespread, state-of-the-art approaches in the literature have mainly focused on detecting the so-called static placement frauds, where only a single UI state is involved and can be identified based on static information such as the size or location of ad views. Other types of fraud exist that involve multiple UI states and are performed dynamically while users interact with the app. Such dynamic interaction frauds, although now widely spread in apps, have not yet been explored nor addressed in the literature. In this work, we investigate a wide range of mobile ad frauds to provide a comprehensive taxonomy to the research community. We then propose, FraudDroid, a novel hybrid approach to detect ad frauds in mobile Android apps. Fraud- Droid analyses apps dynamically to build UI state transition graphs and collects their associated runtime network traffics, which are then leveraged to check against a set of heuristic-based rules for identifying ad fraudulent behaviours. We show empirically that FraudDroid detects ad frauds with a high precision (∼93%) and recall (∼92%). Experimental results further show that FraudDroid is capable of detecting ad frauds across the spectrum of fraud types. By analysing 12,000 ad-supported Android apps, FraudDroid identified 335 cases of fraud associated with 20 ad networks that are further confirmed to be true positive results and are shared with our fellow researchers to promote advanced ad fraud detection.
KW - ad fraud
KW - Android
KW - automation
KW - mobile app
KW - user interface
UR - http://www.scopus.com/inward/record.url?scp=85058180223&partnerID=8YFLogxK
U2 - 10.1145/3236024.3236045
DO - 10.1145/3236024.3236045
M3 - Conference Paper
AN - SCOPUS:85058180223
SP - 257
EP - 268
BT - ESEC/FSE'18 - Proceedings of the 2018 26th ACM Joint Meeting on European Software Engineering Conference and Symposium on the Foundations of Software Engineering
A2 - Leavens, Gary T.
A2 - Garcia, Alessandro
A2 - Pasareanu, Corina S.
PB - Association for Computing Machinery (ACM)
CY - New York NY USA
ER -