The dark side of micro-task marketplaces: Characterizing fiverr and automatically detecting crowdturfing

As human computation on crowdsourcing systems has be-come popular and powerful for performing tasks, malicious users have started misusing these systems by posting ma-licious tasks, propagating manipulated contents, and target-ing popular web services such as online social networks and search engines. Recently, these malicious users moved to Fiverr, a fast-growing micro-task marketplace, where work-ers can post crowdturfing tasks (i.e., astroturfing campaigns run by crowd workers) and malicious customers can pur-chase those tasks for only $5. In this paper, we present a comprehensive analysis of Fiverr. First, we identify the most popular types of crowdturfing tasks found in this market-place and conduct case studies for these crowdturfing tasks. Then, we build crowdturfing task detection classifiers to fil-ter these tasks and prevent them from becoming active in the marketplace. Our experimental results show that the pro-posed classification approach effectively detects crowdturf-ing tasks, achieving 97.35 % accuracy. Finally, we analyze the real world impact of crowdturfing tasks by purchasing active Fiverr tasks and quantifying their impact on a target site. As part of this analysis, we show that current security systems inadequately detect crowdsourced manipulation, which con-firms the necessity of our proposed crowdturfing task detec-tion approach