Data Poisoning Attacks and Defenses to Crowdsourcing Systems
Date
2021-06-03
Authors
Major Professor
Advisor
Committee Member
Journal Title
Journal ISSN
Volume Title
Publisher
Association for Computing Machinery
Abstract
A key challenge of big data analytics is how to collect a large volume of (labeled) data. Crowdsourcing aims to address this challenge via aggregating and estimating high-quality data (e.g., sentiment label for text) from pervasive clients/users. Existing studies on crowdsourcing focus on designing new methods to improve the aggregated data quality from unreliable/noisy clients. However, the security aspects of such crowdsourcing systems remain under-explored to date. We aim to bridge this gap in this work. Specifically, we show that crowdsourcing is vulnerable to data poisoning attacks, in which malicious clients provide carefully crafted data to corrupt the aggregated data. We formulate our proposed data poisoning attacks as an optimization problem that maximizes the error of the aggregated data. Our evaluation results on one synthetic and two real-world benchmark datasets demonstrate that the proposed attacks can substantially increase the estimation errors of the aggregated data. We also propose two defenses to reduce the impact of malicious clients. Our empirical results show that the proposed defenses can substantially reduce the estimation errors of the data poisoning attacks.
Series Number
Journal Issue
Is Version Of
Versions
Series
Academic or Administrative Unit
Type
conference presentation
Comments
This proceeding is published as Minghong Fang, Minghao Sun, Qi Li, Neil Zhenqiang Gong, Jin Tian, and Jia Liu. 2021. Data Poisoning Attacks and Defenses to Crowdsourcing Systems. In Proceedings of the Web Conference 2021 (WWW '21). Association for Computing Machinery, New York, NY, USA, 969–980. https://doi.org/10.1145/3442381.3450066. © 2021 IW3C2 (International World Wide Web Conference Committee), under Creative Commons CC-BY 4.0 License.