The Future of Search Rank Fraud Research
Search rank fraud consists in posting large numbers of fake activities for products hosted in commercial peer-opinion services such as those provided by Google, Apple, Amazon. Search rank fraud is often carried out by hiring professional workers (see below for photo) who control many user accounts and devices, and seeks to give the illusion of grassroots engagement, thus boost financial gains, promote malware and even assist censorship efforts.
Existing fraud detection efforts are often based on axiomatic assumptions on how workers operate. Such assumptions are introduced based on intuition or are extracted from small datasets of fraud, or are revealed by collaborators within peer-opinion sites. However, to the best of our knowledge these assumptions have never been validated, i.e., verified that they indeed correspond, or continue to correspond to how professional workers actually operate.
In this project we argue that knowledge of the authentic capabilities, behaviors and strategies employed by empirically validated workers, is paramount to develop solutions that efficiently manage and contain search rank fraud. To achieve this, we conducted qualitative and quantitative investigations with professional workers concerning activities they performed on Google Play, and reveal findings concerning their capabilities, working patterns and strategies to avoid fraud detection.
Mizanur Rahman*, Nestor Hernandez*, Ruben Recabarren, Syed Ishtiaque Ahmed, Bogdan Carbunar. (* equally contributing authors).
In Proceedings of the 26th ACM Conference on Computer and Communications Security (CCS), London, November 2019. [pdf]
FundingThis work has been partially funded through generous support from:
- NSF 1840714 and NSF 1527153