Visible to the public Automated Crowdturfing Attacks and Defenses in Online Review Systems

TitleAutomated Crowdturfing Attacks and Defenses in Online Review Systems
Publication TypeConference Paper
Year of Publication2017
AuthorsYao, Yuanshun, Viswanath, Bimal, Cryan, Jenna, Zheng, Haitao, Zhao, Ben Y.
Conference NameProceedings of the 2017 ACM SIGSAC Conference on Computer and Communications Security
PublisherACM
Conference LocationNew York, NY, USA
ISBN Number978-1-4503-4946-8
Keywordscrowdtur ng, fake review, Human Behavior, Metrics, opinion spam, pubcrawl, Scalability, spam detection, web security
Abstract

Malicious crowdsourcing forums are gaining traction as sources of spreading misinformation online, but are limited by the costs of hiring and managing human workers. In this paper, we identify a new class of attacks that leverage deep learning language models (Recurrent Neural Networks or RNNs) to automate the generation of fake online reviews for products and services. Not only are these attacks cheap and therefore more scalable, but they can control rate of content output to eliminate the signature burstiness that makes crowdsourced campaigns easy to detect. Using Yelp reviews as an example platform, we show how a two phased review generation and customization attack can produce reviews that are indistinguishable by state-of-the-art statistical detectors. We conduct a survey-based user study to show these reviews not only evade human detection, but also score high on "usefulness" metrics by users. Finally, we develop novel automated defenses against these attacks, by leveraging the lossy transformation introduced by the RNN training and generation cycle. We consider countermeasures against our mechanisms, show that they produce unattractive cost-benefit tradeoffs for attackers, and that they can be further curtailed by simple constraints imposed by online service providers.

URLhttp://doi.acm.org/10.1145/3133956.3133990
DOI10.1145/3133956.3133990
Citation Keyyao_automated_2017