arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 2102.09171cs.CRcs.DCcs.HCcs.LG
收藏

众包系统的数据投毒攻击与防御

Data Poisoning Attacks and Defenses to Crowdsourcing Systems

Iowa State University(爱荷华州立大学);The Ohio State University(俄亥俄州立大学);Duke University(杜克大学)

Minghong Fang, Minghao Sun, Qi Li, Neil Zhenqiang Gong, Jin Tian, Jia Liu

摘要:

大数据分析的一个关键挑战是如何收集大量的(标记的)数据。众包旨在通过聚合和估计高质量数据(例如,文本的情感标签)。现有的众包研究集中在设计新的方法,以提高不可靠/嘈杂的客户端的聚合数据的质量。然而,这种众包系统的安全方面迄今为止仍然没有得到充分的探索。我们的目标是在这项工作中弥合这一差距。具体来说,我们表明,众包是容易受到数据投毒攻击,其中恶意客户端提供精心制作的数据,以破坏聚合数据。我们制定我们提出的数据投毒攻击作为一个优化问题,最大限度地提高聚合数据的错误。我们对一个合成数据集和两个真实世界基准数据集的评估结果表明,所提出的攻击可以大大增加聚合数据的估计误差。我们还提出了两种防御措施,以减少恶意客户端的影响。我们的实证结果表明,所提出的防御可以大大减少数据投毒攻击的估计误差。

英文摘要:

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.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑