An ensemble learning based approach for impression fraud detection in mobile advertising

Abstract Mobile advertising enjoys 51% share of the whole digital market nowadays. The advertising ecosystem faces a major threat from ad frauds caused by false display requests or clicks, generated by malicious codes, bot-nets, click-firms etc. Around 30% revenue is being wasted due to frauds. Ad frauds in web advertising have been studied extensively, however frauds in mobile advertising have received little attention. Studies have been conducted to detect fraudulent clicks in web and mobile advertisement. However, detection of individual fraudulent display in mobile advertising is yet to be explored to the best of our knowledge. We have proposed an ensemble based method to classify each individual ad display, also called an impression, as fraudulent or non-fraudulent. Our solution achieves as high as 99.32% accuracy, 96.29% precision and 84.75% recall using real datasets from an European commercial ad server. We have proposed some new features and analyzed their contribution using standard techniques. We have also designed a new mechanism to offer flexibility of tolerance to different ad servers in deciding whether an ad display is fraudulent or not.

[1]  Helen J. Wang,et al.  User-Driven Access Control: Rethinking Permission Granting in Modern Operating Systems , 2012, 2012 IEEE Symposium on Security and Privacy.

[2]  Andreas Terzis,et al.  A multifaceted approach to understanding the botnet phenomenon , 2006, IMC '06.

[3]  Nitesh V. Chawla,et al.  SMOTE: Synthetic Minority Over-sampling Technique , 2002, J. Artif. Intell. Res..

[4]  Ron Kohavi,et al.  Wrappers for Feature Subset Selection , 1997, Artif. Intell..

[5]  Ryan Stevens,et al.  MAdFraud: investigating ad fraud in android applications , 2014, MobiSys.

[6]  Yin Zhang,et al.  Measuring and fingerprinting click-spam in ad networks , 2012, SIGCOMM.

[7]  Divyakant Agrawal,et al.  Using Association Rules for Fraud Detection in Web Advertising Networks , 2005, VLDB.

[8]  Chinya V. Ravishankar,et al.  Addressing Click Fraud in Content Delivery Systems , 2007, IEEE INFOCOM 2007 - 26th IEEE International Conference on Computer Communications.

[9]  Markus Jakobsson,et al.  Combating Click Fraud via Premium Clicks , 2007, USENIX Security Symposium.

[10]  S. Savage,et al.  Got traffic?: an evaluation of click traffic providers , 2011, WebQuality '11.

[11]  Wei Lee Woon,et al.  A Novel Ensemble Learning-Based Approach for Click Fraud Detection in Mobile Advertising , 2013, MIKE.

[12]  Qifa Ke,et al.  SBotMiner: large scale search bot detection , 2010, WSDM '10.

[13]  Christopher Krügel,et al.  Understanding fraudulent activities in online ad exchanges , 2011, IMC '11.

[14]  Paul Barford,et al.  Impression Fraud in On-line Advertising via Pay-Per-View Networks , 2013, USENIX Security Symposium.

[15]  Jie Liu,et al.  DECAF: Detecting and Characterizing Ad Fraud in Mobile Apps , 2014, NSDI.

[16]  David Lo,et al.  Detecting click fraud in online advertising: a data mining approach , 2014, J. Mach. Learn. Res..

[17]  Divyakant Agrawal,et al.  SLEUTH: Single-pubLisher attack dEtection Using correlaTion Hunting , 2008, Proc. VLDB Endow..

[18]  Divyakant Agrawal,et al.  Duplicate detection in click streams , 2005, WWW '05.

[19]  Hamed Haddadi,et al.  Fighting online click-fraud using bluff ads , 2010, CCRV.

[20]  Hyoungshick Kim,et al.  Combating online fraud attacks in mobile-based advertising , 2016, EURASIP J. Inf. Secur..

[21]  Divyakant Agrawal,et al.  Detectives: detecting coalition hit inflation attacks in advertising networks streams , 2007, WWW '07.