An Ensemble Learning Approach to Detect Touch-Spam in Mobile Ad-Networks

International Journal of P2P Network Trends and Technology (IJPTT)          
© 2017 by IJPTT Journal
Volume - 7 Issue - 2
Year of Publication : 2017
Authors : M.Sree Vani


M.Sree Vani "An Ensemble Learning Approach to Detect Touch-Spam in Mobile Ad-Networks". International Journal of P2P Network Trends and Technology (IJPTT), V7(2):18-24 Mar - Apr 2017, ISSN:2249-2615,, Published by Seventh Sense Research Group.


A touch user interface (TUI) is a computer-pointing technology based upon the sense of touch (haptics). Touch-spam is a type of fraud that occurs over TUI gadgets ex. Smart phones, tablets, phablets, touch laptops etc. It actually happens in TUI applications when a person, automated script, computer program or robotic action imitates a legitimate user of a TUI application touching on an advertisement (ad), for the purpose of generating a charge per touch without having actual interest in the target of the ad’s popup. Touch-spam is becoming an issue due to the advertising networks being a key beneficiary of this spam. In present days, smart phone gaming applications (apps) are playing a vital role to attract mobile-advertisements (ads) since their pocket portability and other versatile features. Popular apps are able to read the user personalized data to process user interests helping to generate customized ads. Touch-spam in smart phone apps is a fraudulent or invalid tap or touch on online ads, where the user has no actual interest in the advertiser’s site. It requires a user touch on online ads that pop-up dynamically in smart phone gaming apps. It all need the user to tap the screen close to where the ad is displayed .While the ad networks continue taking active measures to block click-spam today, the touch-spam still creeping under the TUI. It is being used by spammers to misappropriate the advertising revenue. The presence of touch-spam is largely unknown. In this paper, we take the first systematic look at touch-spam. We propose an ensemble learning approach to identify touch-spam Apps in Smartphone-game Apps. We validate our methodology using data from major ad networks. Our findings highlight the severity of the touch-spam problem.


[1] S.Ganov, C. Killmar, S. Khurshid, and D. Perry. Event listener analysis and symbolic execution for testing gui applications. In ICFEM, 2009.
[2] Google admob.
[3] iad app network.
[4] Microsoft advertising.
[5] S.Alrwais, A. Gerber, C. Dunn, O. Spatscheck,M. Gupta, and E.Osterweil. Dissecting ghost clicks: Ad fraud via misdirected human clicks. In ACSAC, 2012.
[6] T.Blizard and N. Livic. Click-fraud monetizing malware: A survey and case study. In MALWARE,2012.
[7] P.Chia, Y. Yamamoto, and N. Asokan. Is this app safe? a large scale study on application permissions and risk signals. In WWW, 2012.
[8] V.Dave, S. Guha, and Y. Zhang. Measuring and fingerprinting click-spam in ad networks. In ACM SIGCOMM, 2012.
[9] C.Cadar D. Dunbar and D. Engler. Klee: Unassisted and automatic generation of high-coverage tests for complex systems programs. In USENIX OSDI, 2008.
[10] P.Gilbert, B. Chun, L. Cox, and J. Jung. Vision:automated security validation of mobile apps at app markets. In MCS, 2011.
[11] H.Haddadi. Fighting online click-fraud using bluff ads. ACM Computer Communication Review, 40(2):21–25, 2010.14
[12] C.Hu and I. Neamtiu. Automating gui testing for android applications. In AST, 2011.
[13] A.MacHiry, R. Tahiliani, and M. Naik. Dynodroid: An input generation system for android apps. In FSE, 2013.
[14] A.Mesbah and A. van Deursen. Invariant-based automatic testing of ajax user interfaces. In ICSE, 2009. Conference [15] Ali Mesbah, Arie van Deursen, and Stefan Lenselink. Crawling ajax-based web applications through dynamic analysis of user interface state changes. ACM Transactions on the Web, 6(1):1–30, 2012.
[15] A.Metwally, D. Agrawal, and A. El Abbadi. Detectives:Detecting coalition hit inflation attacks in advertising networks streams. In WWW, 2007.
[16] A.Metwally, F. Emekci, D. Agrawal, and A. El Abbadi.Sleuth: Single-publisher attack detection using correlation hunting. In PVLDB, 2008.
[17] B.Miller, P. Pearce, C. Grier, C. Kreibich, and V. Paxson. What’s clicking what? techniques and
[18] innovations of today’s clickbots. In DIMVA, 2011. [19] L. Ravindranath, J. Padhye, S. Agarwal, R. Mahajan,I. Obermiller, and S. Shayandeh. Appinsight:
[19] mobile app performance monitoring in the wild. In USENIX OSDI, 2012.
[20] W.Yang, M. Prasad, and T. Xie. A grey-box approach for automated gui-model generation of mobile applications. In FASE, 2013.
[21] M.Najork. Web spam detection. In L. Liu and M. T.•Ozsu, editors, Encyclopedia of Database Systems, pages 3520{3523. Springer US, 2009.
[22] Nick Bilton. Disruptions: So Many Apologies, So Much Data Mining., 2012.
[23] Peter Gilbert, Byung-Gon Chun, Landon P Cox, and Jaeyeon Jung. Vision: automated security validation of mobile apps at app markets. In Proceedings of the second international workshop on Mobile cloud computing and services - MCS `11, page 21, New York, New York, USA, 2011. ACM Press.
[24] Google admob: What’s the difference between estimated and finalized earnings? http://support.
[25] Microsoft advertising: Build your business. http: //
[26] iad app network.
[27] Admob publisher guidelines and policies. topic=1307235.
[28] Microsoft pubcenter publisher terms and conditions. en.html.
[29] L.Breiman. Bagging predictors. Machine Learning,24(2):123{140, 1996.
[30] Y.Freund and R. E. Schapire. A decision-theoretic generalization of on-line learning and an application to boosting. In European Conference on Computational Learning Theory, pages 23{37, 1995.

Spam, mobile apps, touch spam, click spam